Add a staged implementation plan for background context references

.gitignore

@@ -1,3 +1,6 @@
+# build artifacts
+./notarius
+
 # ---> Go
 # If you prefer the allow list template instead of the deny list, see community template:
 # https://github.com/github/gitignore/blob/main/community/Golang/Go.AllowList.gitignore
@@ -49,6 +52,7 @@ go.work.sum
 # Icon must end with two \r
 Icon
 
+
 # Thumbnails
 ._*
 

AGENTS.md

@@ -1,3 +1,6 @@
-Please carefully review the documents in `docs/policy` before making any changes to this repository.
- - `architecture.md` provides the canonical high-level architecture policy for this repository.
- - `documentation.md` provides the canonical documentation policy for this repository.
+Please review `docs/internal/overview.md` for initial orientation in this repository.
+
+Additionally, please carefully review the relevant documents in `docs/policy` before making any changes to this repository.
+ - `development.md` defines the contributor workflow for this application.
+ - `architecture.md` provides the canonical high-level architecture policy for this repository, and should be reviewed before writing or changing any code.
+ - `documentation.md` provides the canonical documentation policy for this repository, and should be reviewed before writing or changing any documentation.

docs/cli.md

@@ -117,7 +117,7 @@ go run ./cmd/notarius pipelines list \
 The production CLI currently registers these module keys:
 
 - input: `seriatim`
-- chunk: `generic`
+- chunk: `generic`, `dnd/scenes`
 - extract: `dnd/spells`
 - merge: `appendorder`
 - normalize: `noop`

docs/config.md

@@ -167,6 +167,7 @@ one configured profile.
 | --- | --- | --- |
 | input | `seriatim` | Reads Seriatim transcript JSON. |
 | chunk | `generic` | Splits source units into ordered chunks. |
+| chunk | `dnd/scenes` | Uses an LLM to split transcript source units into D&D scenes. |
 | extract | `dnd/spells` | Extracts `dnd.spell_cast` artifacts. |
 | merge | `appendorder` | Keeps candidates in append order. |
 | normalize | `noop` | Passes merged artifacts through unchanged. |
@@ -178,6 +179,9 @@ The `generic` chunker accepts:
 - `overlap_units`: non-negative integer, default `0`, and must be less than
   `max_units`.
 
+The `dnd/scenes` chunker requires transcript source capabilities, calls the
+configured structured LLM provider, and does not accept module options.
+
 ## Diagnostics
 
 `diagnostics` fields:

docs/integrations/json-output.md

@@ -57,7 +57,19 @@ approved.
   "pipeline_id": "dnd-session",
   "pipeline_digest": "sha256:...",
   "input_module": "seriatim",
-  "chunker": "generic",
+  "chunker": "dnd/scenes",
+  "module_metadata": {
+    "chunker": {
+      "prompt_id": "dnd.scenes",
+      "prompt_version": "v1",
+      "prompt_sha256": "sha256:...",
+      "response_schema_key": "dnd_scenes",
+      "response_schema_id": "notarius.dnd.scenes",
+      "response_schema_name": "notarius_dnd_scenes_v1",
+      "response_schema_version": "v1",
+      "response_schema_sha256": "sha256:..."
+    }
+  },
   "source_digests": ["sha256:..."],
   "extractors": ["dnd/spells"],
   "merger": "appendorder",
@@ -86,9 +98,15 @@ approved.
 
 Fields with empty values may be omitted by JSON encoding.
 
+`module_metadata` is omitted when no singleton module provides metadata.
+
 `validation_status` is `approved` when no candidates were rejected and
 `rejected` when one or more candidates were rejected.
 
+Top-level `module_metadata` is reserved for singleton pipeline modules
+(`input`, `chunker`, and `output`). Lane-owned module metadata remains under
+`artifact_lanes[].metadata`.
+
 ## Artifact Files
 
 Each artifact file has this shape:

docs/internal/modules.md

@@ -20,6 +20,11 @@ A production module package should provide:
 Module specs should describe capabilities accurately. Resolution uses specs to
 reject incompatible pipelines before execution.
 
+Chunk modules receive the structured LLM client through `contracts.ChunkRequest`
+when they need model-backed chunking. The pipeline runner validates generic
+chunk result invariants before extraction; module-owned policies may be stricter
+but must stay within the module package.
+
 ## `seriatim` Input
 
 Package: `internal/modules/input/seriatim`
@@ -44,6 +49,10 @@ The `generic` chunker splits source units into ordered chunks. It validates the
 source document, clones source units, assigns chunk IDs such as `chunk-000001`,
 and records chunk metadata for start unit, end unit, and unit count.
 
+The pipeline runner canonicalizes chunk units from the source document by ID
+before extractors and mergers run. Chunker-owned context should stay in
+`SourceChunk.Metadata`.
+
 Options:
 
 - `max_units`: positive integer, default `50`;
@@ -54,6 +63,39 @@ Provides:
 
 - `chunks`
 
+## `dnd/scenes` Chunker
+
+Package: `internal/modules/chunk/dnd/scenes`
+
+The `dnd/scenes` chunker uses the structured LLM client to divide transcript
+source units into coherent D&D scenes. It renders embedded prompts, loads the
+embedded structured response schema, validates model-authored source-unit
+boundaries, and converts each scene into a deterministic source chunk.
+
+Requires:
+
+- `source.transcript`
+
+Provides:
+
+- `chunks`
+- `chunks.scenes`
+
+Options: none. Non-empty options are rejected.
+
+The chunker enforces full source-unit coverage from the first source unit to the
+last, exact source-unit IDs, sequential contiguous scenes, and no overlap. It
+assigns chunk IDs such as `scene-000001` and stores scene metadata including
+title, primary mode, participants, summary, boundary note, confidence, boundary
+unit IDs, and unit count. Boundary caveats become warnings with reason code
+`scene_boundary_caveat`. Whitespace-only caveats are treated as malformed
+structured output rather than silently dropped.
+
+Malformed model output fails explicitly rather than falling back to another
+chunker. The chunker exposes prompt and response-schema provenance through
+top-level `module_metadata.chunker` without raw prompts, raw schemas, source
+text, or secrets.
+
 ## `dnd/spells` Extractor
 
 Package: `internal/modules/extract/dnd/spells`
@@ -78,7 +120,8 @@ Artifact type and schema version:
 - schema version: `v1`
 
 The extractor adds prompt and response-schema provenance to lane manifest
-metadata. Durable artifact payload details belong in the
+metadata under `artifact_lanes[].metadata.extractor`. Durable artifact payload
+details belong in the
 [D&D spell artifact contract](../integrations/dnd-spell-artifacts.md).
 
 ## D&D Spell Validators

docs/internal/pipeline.md

@@ -73,8 +73,39 @@ The runner:
 2. builds the input adapter and parses the raw input into a source document;
 3. validates the source document;
 4. builds the chunker and produces source chunks;
-5. runs each selected artifact lane in sorted resolved order;
-6. builds the output encoder and validates logical output file names.
+5. validates source chunks against framework invariants;
+6. runs each selected artifact lane in sorted resolved order;
+7. builds the output encoder and validates logical output file names.
+
+## Chunk Results
+
+Chunkers implement `contracts.Chunker` and receive a `contracts.ChunkRequest`
+with the validated source document, the structured LLM client, the configured
+LLM profile, module options, and run metadata. Deterministic and LLM-backed
+chunkers use the same contract; provider construction stays outside chunk
+modules.
+
+After `Chunk` returns, the runner appends chunker warnings before returning any
+chunker error. When chunking succeeds, the runner validates generic chunk
+invariants before running extractors:
+
+- chunk IDs must be non-empty and unique in the chunk result;
+- each chunk `SourceID` must match the source document ID;
+- each chunk `Index` must match its zero-based returned order;
+- each chunk must contain at least one source unit;
+- a chunk must not repeat a source unit;
+- every chunk source unit must exist in the source document;
+- source units inside each chunk must appear in source-document order.
+
+After validation, the runner rebuilds each chunk from source-document units by
+ID, preserving the chunk boundary order and cloning chunk metadata. Extractors
+and downstream stages therefore see canonical source units, while
+`SourceChunk.Metadata` remains the supported place for chunker-owned context.
+
+The framework does not require complete source-unit coverage and does not reject
+overlap between different chunks. Stricter policies, such as full coverage or
+non-overlap, belong to individual chunk modules when they are part of that
+module's contract.
 
 Within an artifact lane, the runner:
 
@@ -119,9 +150,15 @@ On successful execution, the manifest validation status is:
 
 ## Manifest Population
 
-The manifest records run ID, pipeline ID, pipeline digest, module keys, artifact
-lanes, LLM profile metadata, source digest, validation status, and timing.
+The manifest records run ID, pipeline ID, pipeline digest, module keys, top-level
+module metadata, artifact lanes, LLM profile metadata, source digest,
+validation status, and timing.
 
-Modules can add non-secret manifest metadata by implementing
-`contracts.ManifestMetadataProvider`. The D&D spell extractor uses this for
+Singleton pipeline modules may add non-secret metadata by implementing
+`contracts.ManifestMetadataProvider`. The runner records that metadata under
+`module_metadata` with stable keys for `input`, `chunker`, and `output`.
+
+Lane-owned modules may add non-secret metadata through
+`artifact_lanes[].metadata`. The runner records extractor, merger, and
+normalizer metadata there. The D&D spell extractor uses lane metadata for
 prompt and response-schema provenance.

docs/operations.md

@@ -34,8 +34,8 @@ The `json` output module writes these files:
 
 - `index.json`: file index with paths to the manifest, artifact files,
   rejected artifacts, and warnings.
-- `manifest.json`: run manifest with resolved pipeline provenance, module keys,
-  validation status, and timing.
+- `manifest.json`: run manifest with resolved pipeline provenance, top-level
+  module metadata, module keys, validation status, and timing.
 - `artifacts/<artifact-type>.json`: approved artifacts grouped by artifact
   type. For the current D&D spell extractor, this includes
   `artifacts/dnd.spell_cast.json` when spell-cast artifacts are approved.
@@ -63,7 +63,7 @@ Implemented diagnostics artifacts:
 - `effective-config.json`: resolved config with API keys redacted.
 - `resolved-pipeline.json`: resolved module bindings and pipeline digest.
 - `run-manifest.json`: the same run manifest written to durable output when it
-  is available.
+  is available, including top-level module metadata when present.
 - `warnings.json`: warning list.
 - `run-report.json`: counts, status, output path, diagnostics path, and run ID.
 - `error.log`: failure message, written after diagnostics directory creation

docs/roadmap/implementation.md

@@ -0,0 +1,305 @@
+# Extraction References Implementation Plan
+
+## Purpose
+
+Implement the extraction-reference feature described in
+[references.md](references.md). This plan is decision-complete for an LLM coding
+agent: implement each stage in order, keep the repository compiling after each
+stage, and do not move planned behavior into non-roadmap docs until the relevant
+behavior exists.
+
+Core decisions to preserve:
+
+- references are opaque framework inputs and domain semantics stay in extract
+  modules;
+- references are not evidence and must not be addressable through `SourceRef`;
+- reference binding is lane-scoped;
+- extractors expose `ReferenceSlots()` directly on the first-class extractor
+  contract;
+- token budgeting is deferred; enforce only UTF-8 text handling, empty-file
+  warnings, and declared `MaxBytes`;
+- run manifests record references in a dedicated section, separate from
+  `source_digests`;
+- CLI unbinding uses `--without-reference`.
+
+## Stage 1: Contracts and Mechanical Adoption
+
+Add the framework contracts needed to describe references without changing
+runtime behavior. Slot declarations must be available without constructing
+extractor modules, because pipeline/config validation should use registry
+metadata rather than runtime module instances.
+
+Implementation steps:
+
+- In `internal/framework/contracts`, add reference model types:
+  `ReferenceSlot`, `ReferenceOrigin`, `ReferenceItem`,
+  `ResolvedReferenceSlot`, `ReferenceSet`, and a binding-source enum or string
+  constants for `config` and `cli`.
+- Include `Name`, `Description`, `Required`, `AcceptedMediaTypes`, `Multiple`,
+  and `MaxBytes` on `ReferenceSlot`.
+- Include slot name, media type, content bytes, digest, origin, size bytes, and
+  binding source on `ReferenceItem`.
+- Add `References ReferenceSet` to `contracts.ExtractionRequest`.
+- Add `ReferenceSlots() []ReferenceSlot` to `contracts.Extractor`.
+- Extend extractor registration metadata so reference slots are also declared
+  through the extractor's registry spec. Prefer the smallest idiomatic change to
+  the existing registry model, such as adding `ReferenceSlots` to `ModuleSpec`
+  with validation that non-extractor modules leave it empty, unless the codebase
+  shape clearly supports a narrower extractor-specific spec.
+- Update every concrete extractor and all extractor fakes/test doubles to
+  implement `ReferenceSlots()`. Existing extractors without references should
+  return `nil`.
+- Add tests that compare a production extractor's runtime `ReferenceSlots()`
+  with its registered spec slots so the two declarations cannot drift.
+- Add contract tests for empty reference sets, slot copying expectations if
+  helpers are introduced, and compile-time coverage through existing fakes.
+
+Verification:
+
+- `go test ./internal/framework/contracts`
+- `go test ./internal/framework/pipeline`
+- `go test ./...`
+
+## Stage 2: Config Shape and Pipeline-Level Resolution
+
+Add unresolved reference bindings to config and resolved lane bindings to the
+pipeline model. Do not read reference files in this stage.
+
+Implementation steps:
+
+- Add `references` maps to file config parsing at both pipeline and artifact
+  lane level.
+- Add corresponding fields to `pipeline.PipelineProfile` and
+  `pipeline.ArtifactLaneProfile`.
+- Preserve deterministic map handling and duplicate-after-trim validation.
+- Extend config cloning, effective config, redaction, validation, and tests for
+  the new fields.
+- Add resolved reference binding structures to `internal/framework/pipeline`.
+  They should represent lane ID, slot name, source URI/path, and binding source,
+  but not file bytes.
+- During `pipeline.ResolvePipeline`, collect selected lanes, read each lane
+  extractor's declared slots from registry metadata, and validate without
+  building extractor instances:
+  - every bound slot is declared by the lane extractor;
+  - required slots are bound after applying pipeline-level and lane-level config;
+  - required slots remain bound after any CLI unbinds supplied to resolution;
+  - selected lanes under `--only` are the only lanes considered.
+- Apply pipeline-level bindings as defaults only to lanes whose extractor
+  declares the matching slot.
+- Apply lane-level bindings as overrides or additions for that lane.
+- Keep reference bindings out of source digests and artifact source references.
+- Add tests proving reference-slot validation works through registry specs even
+  when extractor constructors would fail if called.
+
+Verification:
+
+- `go test ./internal/core/config`
+- `go test ./internal/framework/pipeline`
+- `go test ./...`
+
+## Stage 3: CLI Reference Overrides and Unbinds
+
+Add run-time CLI syntax for reference binding overrides and optional unbinding.
+
+Implementation steps:
+
+- Add repeatable `--reference` flags to `notarius run`.
+  Accepted forms:
+  - `slot=path` for unambiguous slot names across selected lanes;
+  - `lane.slot=path` for explicit lane-scoped binding.
+- Add repeatable `--without-reference` flags to `notarius run`.
+  Accepted forms:
+  - `slot`;
+  - `lane.slot`.
+- Reject empty paths for `--reference`; use `--without-reference` for unbinding.
+- Reject malformed values with concise CLI errors before expensive work.
+- Pass parsed override/unbind requests into config/pipeline resolution.
+- Resolve flat CLI names only when exactly one selected lane declares the slot.
+  If multiple selected lanes declare the same slot, fail and instruct the user
+  to use `lane.slot`.
+- Let CLI bindings override config bindings for the same lane and slot.
+- Let CLI unbinds remove config-bound optional slots for the same lane and slot.
+- Fail if unbinding leaves a required slot unbound.
+- Add CLI tests for flat binding, lane-qualified binding, ambiguous flat
+  binding, malformed syntax, optional unbind, and required-slot unbind failure.
+
+Verification:
+
+- `go test ./internal/cli`
+- `go test ./internal/core/config`
+- `go test ./internal/framework/pipeline`
+- `go test ./...`
+
+## Stage 4: Run Preparation and Reference Materialization
+
+Read, validate, digest, and materialize resolved file references before any LLM
+call.
+
+Implementation steps:
+
+- Add a reference resolver/materializer near pipeline run preparation. Keep file
+  I/O out of pure config parsing.
+- Ensure run preparation receives the loaded config path or config directory so
+  config-relative reference paths can be resolved after pure config parsing.
+- Resolve config-relative paths relative to the config file path and
+  CLI-relative paths relative to the current working directory.
+- For MVP, accept only UTF-8 text files. Reject non-UTF-8 content with an error
+  naming pipeline, lane, slot, and path.
+- Compute `sha256:` content digests over the raw reference bytes.
+- Populate `ReferenceItem` values with content bytes, media type, digest,
+  origin type `file`, normalized origin URI/path, size bytes, and binding source.
+- Enforce declared `MaxBytes` when greater than zero. The error should name the
+  pipeline, lane, slot, actual size, limit, and path.
+- Emit a warning for empty bound files, but do not fail.
+- Add `ReferenceSet` values to the runner input or resolved pipeline path in a
+  way that keeps lane-scoped references available when calling each extractor.
+- Pass the correct lane-specific `ReferenceSet` into
+  `contracts.ExtractionRequest`.
+- Ensure no reference content is written to ordinary diagnostics, logs, errors,
+  or manifests.
+
+Verification:
+
+- Focused resolver/materializer tests for path resolution, digest stability,
+  UTF-8 rejection, empty-file warning, `MaxBytes`, and binding source.
+- `go test ./internal/cli`
+- `go test ./internal/framework/pipeline`
+- `go test ./...`
+
+## Stage 5: Prompt Template Reference Functions
+
+Make references available to module-owned prompt templates.
+
+Implementation steps:
+
+- Extend `internal/framework/prompt` so prompt bundles can be compiled with
+  declared reference slots.
+- Add `reference` and `hasreference` template functions.
+- Validate at bundle build time, or the earliest feasible equivalent, that
+  templates reference only declared slots.
+- Render a declared but unbound optional slot as an empty string.
+- Ensure `hasreference` returns true only when the slot has at least one bound
+  item with content.
+- Render multiple items deterministically if future `Multiple` support is
+  enabled; for MVP, reject multiple bindings unless the slot declares
+  `Multiple`.
+- Keep prompt metadata hashes based on template source. Do not include rendered
+  reference content in prompt identity.
+- Add deterministic rendering tests proving byte-identical output across runs
+  with the same reference bytes and config.
+
+Verification:
+
+- `go test ./internal/framework/prompt`
+- `go test ./internal/modules/extract/dnd/spells`
+- `go test ./...`
+
+## Stage 6: Manifest and Diagnostics Provenance
+
+Record reference provenance separately from source provenance.
+
+Implementation steps:
+
+- Add a dedicated references section to `artifacts.RunManifest`.
+  The shape should be lane-scoped and include lane ID, slot name, origin type,
+  origin URI/path, digest, media type, size bytes, and binding source.
+- Do not add reference digests to `source_digests`.
+- Include reference digests in any cache/idempotency key if such a key exists.
+  If no cache/idempotency key exists, add a test or comment documenting that no
+  additional key needs updating yet.
+- Write a diagnostics artifact for resolved references that contains provenance
+  only, not full content, consistent with redacted effective config behavior.
+- Ensure durable JSON output manifests include the new manifest section.
+- Add manifest round-trip tests and a CLI/run test where two runs that differ
+  only in reference bytes produce distinguishable manifests.
+
+Verification:
+
+- `go test ./internal/core/artifacts`
+- `go test ./internal/core/diagnostics`
+- `go test ./internal/modules/output/json`
+- `go test ./internal/cli`
+- `go test ./...`
+
+## Stage 7: D&D Spells Consumer
+
+Use the new reference feature in the first production extractor.
+
+Implementation steps:
+
+- Declare optional `roster` and `glossary` slots on `dnd/spells`.
+- Set accepted media type to text/UTF-8. Add conservative `MaxBytes` limits only
+  if a clear module-owned limit is chosen; otherwise leave `MaxBytes` unset.
+- Update the D&D spells prompt bundle to include conditional reference sections
+  using `hasreference` and `reference`.
+- Frame references as supporting material only. The prompt must instruct the
+  model to extract only spell-cast events present in the source transcript and
+  use references only for disambiguation.
+- Update prompt metadata tests as needed while preserving template-hash
+  semantics.
+- Add fixture coverage with no references, with roster/glossary references, and
+  with a roster that mentions a spell never cast in the transcript. The last
+  case must assert no spell-cast artifact is produced for the uncast spell.
+- If existing deterministic source-reference validation can be extended
+  cleanly, add warning-level relatedness checks for spell names or close
+  variants near cited source text. If this becomes large, defer that validator
+  enhancement to a separate roadmap item and keep the prompt/regression fixture
+  guard in this stage.
+
+Verification:
+
+- `go test ./internal/modules/extract/dnd/spells`
+- `go test ./internal/framework/pipeline`
+- `go test ./internal/cli`
+- `go test ./...`
+
+## Stage 8: Canonical Documentation and Examples
+
+Move implemented behavior out of roadmap-only status once code exists.
+
+Implementation steps:
+
+- Update `docs/cli.md` with `--reference` and `--without-reference` syntax,
+  precedence, ambiguity behavior, and examples.
+- Update `docs/config.md` with pipeline-level and lane-level `references`
+  blocks.
+- Update `docs/internal/modules.md` or the most appropriate internal docs with
+  module-author guidance for `ReferenceSlots()`, reference request delivery,
+  prompt functions, evidence exclusion, and provenance.
+- Update `docs/internal/pipeline.md` with reference resolution lifecycle and
+  lane-scoped delivery.
+- Update `docs/integrations/json-output.md` with the manifest reference
+  provenance shape.
+- Update `docs/operations.md` or `docs/troubleshooting.md` for common reference
+  errors such as unknown slot, ambiguous flat override, missing required slot,
+  unreadable file, non-UTF-8 content, and `MaxBytes` failures.
+- Add maintained example reference files and update `examples/dnd-spells.config.yml`
+  only after the CLI/config behavior is implemented and covered by tests.
+- Keep future-only material in `docs/roadmap/references.md`; do not duplicate
+  canonical current behavior there after implementation.
+
+Verification:
+
+- `rg -n "references:|--reference|--without-reference|ReferenceSlots|reference \"|hasreference" docs examples`
+- `go test ./...`
+- `go vet ./...`
+- `go build ./cmd/notarius`
+
+## Final Acceptance Criteria
+
+The feature is complete when:
+
+- extractor modules can declare reference slots through the first-class
+  extractor contract;
+- config and CLI can bind and unbind lane-scoped file references;
+- selected-pipeline validation catches unknown, ambiguous, or missing required
+  references before any LLM call;
+- run preparation materializes UTF-8 text references with digests, size checks,
+  and empty-file warnings;
+- extractors receive lane-scoped resolved references;
+- prompt templates can render `reference` and `hasreference` deterministically;
+- D&D spell extraction uses optional roster and glossary references;
+- run manifests and diagnostics record reference provenance without recording
+  full content or treating references as source evidence;
+- canonical docs and maintained examples describe only implemented behavior;
+- `go test ./...`, `go vet ./...`, and `go build ./cmd/notarius` pass.

docs/roadmap/references.md

@@ -0,0 +1,238 @@
+# Feature Roadmap: Extraction References
+
+## Status
+
+This document defines the target state and policy choices for the planned
+extraction-reference feature in Notarius. It describes planned behavior, not
+implemented behavior. The staged implementation plan lives in
+[implementation.md](implementation.md).
+
+## Goal
+
+Extraction quality improves when an LLM-backed extractor receives stable
+reference material alongside the source input. For the initial D&D spell
+extractor, useful reference material includes a party roster, a player list, and
+a campaign glossary.
+
+Notarius should support passing this material to extractors as **named reference
+items** without introducing domain-specific concepts into core or framework
+packages. The framework should know only that:
+
+- extractors declare named reference slots they accept;
+- pipeline config and CLI flags bind content, initially files, to those slots;
+- bound content is rendered into module-owned prompt templates;
+- bound content is digested and recorded as run provenance.
+
+Only extract modules should know what a "roster" or "glossary" means. Domain
+semantics live in module-owned slot declarations and prompt templates.
+
+## Definitions
+
+- **Reference slot**: a named, typed-by-convention input declared by an
+  extractor, with a human-readable description, required/optional status, and
+  optional guardrails such as accepted media types and maximum bytes.
+- **Reference item**: resolved content bound to a slot for a given run: slot
+  name, content bytes, media type, content digest, size, origin, and binding
+  source.
+- **Reference binding**: the association of a slot name to a content source,
+  defined in pipeline config and overridable per run via CLI.
+- **Reference set**: the lane-scoped collection of resolved reference items
+  delivered to an extractor.
+
+## Architectural Principles
+
+- References are opaque to the framework. Core and framework packages must not
+  interpret reference content or recognize domain slot names.
+- References are inputs. Anything that can change extraction output must be
+  digested into the run manifest and participate in any cache or idempotency key.
+- References are not evidence. `SourceRef` values must only ever reference
+  source units. Reference items must not receive unit IDs and must not be
+  addressable by source references.
+- Slots are declared, not ad hoc. Binding an undeclared slot name, or omitting a
+  required slot, should fail before any LLM call.
+- Reference delivery is lane-scoped. Pipeline-level bindings may apply to
+  multiple lanes, but each lane receives only the references declared by its
+  extractor after pipeline, lane, CLI override, and CLI unbind rules are
+  resolved.
+- Optional slots degrade gracefully. Prompt templates should render cleanly
+  whether or not an optional slot is bound.
+- Rendering must be deterministic. Identical source input, config, prompts, and
+  reference bytes should produce byte-identical rendered prompts. Reference
+  slots should render in declaration order, with stable binding order within a
+  slot.
+
+## Target Contracts
+
+Extractors should declare accepted reference slots directly on the extractor
+contract. This is a first-class feature, so mechanical updates to existing
+extractors and test fakes are acceptable.
+
+The target slot declaration includes:
+
+- `Name`;
+- `Description`;
+- `Required`;
+- `AcceptedMediaTypes`;
+- `Multiple`;
+- `MaxBytes`.
+
+Extractors with no reference needs return an empty slot list.
+
+Resolved reference items should be content-bearing values, not unresolved file
+paths. The MVP producer is "read this file," but the item shape should permit
+future producers such as prior-run artifacts, derived summaries, or entity
+registries without changing extractor-facing contracts.
+
+The extraction request should carry the lane-scoped resolved reference set.
+Framework and core code should treat the set as opaque bytes plus metadata.
+
+## Binding Lifecycle
+
+Reference handling should be split across existing lifecycle boundaries:
+
+1. Config parsing records pipeline-level and lane-level reference bindings
+   without reading files.
+2. Pipeline resolution validates selected lanes, declared extractor slots,
+   missing required slots, unknown bindings, and ambiguous flat CLI bindings.
+3. Run preparation resolves paths, reads files, validates media type and size,
+   computes digests, and materializes reference items.
+4. Extraction receives the lane-specific resolved reference set.
+
+Config-relative paths resolve relative to the config file. CLI-relative paths
+resolve relative to the current working directory.
+
+## Configuration and CLI
+
+Reference bindings should live in pipeline config because the initial use cases
+are campaign-invariant more often than run-variant. Bindings should be supported
+at two levels:
+
+- pipeline level: defaults shared by artifact lanes whose extractors declare
+  matching slots;
+- lane level: additions or overrides for a single artifact lane.
+
+Illustrative config shape:
+
+```yaml
+pipelines:
+  dnd-session:
+    input: seriatim
+    references:
+      roster: ./campaign/party_roster.md
+      glossary: ./campaign/glossary.md
+    artifacts:
+      spells:
+        extract: dnd/spells
+      npcs:
+        extract: dnd/npcs
+        references:
+          npc_registry: ./campaign/npcs.md
+```
+
+Per-run CLI binding overrides should be repeatable:
+
+```text
+notarius run dnd-session --input session-014.json --reference roster=./alt_roster.md
+```
+
+Flat CLI slot names are allowed when unambiguous across selected lanes. Lane
+qualified names, such as `spells.roster=./alt_roster.md`, disambiguate or target
+a specific lane. CLI bindings override config bindings for the same lane and
+slot.
+
+Users should also be able to unbind a config-bound optional slot for a run with
+an explicit repeatable flag:
+
+```text
+notarius run dnd-session --input session-014.json --without-reference roster
+```
+
+Unbinding a required slot should fail during pipeline/reference resolution.
+
+## Prompt Template Integration
+
+Prompt templates are module-owned. Template rendering should expose:
+
+- `{{ reference "roster" }}`: renders the content of the bound item;
+- `{{ hasreference "glossary" }}`: predicate for conditional sections, so
+  optional slots can be included only when bound.
+
+Rules:
+
+- Referencing an undeclared slot from a template is a module bug and should fail
+  at prompt registration/build time or the earliest feasible equivalent.
+- Referencing a declared but unbound optional slot should render as empty;
+  templates should use `hasreference` to avoid dangling section headers.
+- Rendering must be deterministic and independent of map iteration order.
+- Prompt identity should be computed over the template, not the rendered prompt.
+  Reference digests are recorded separately in the manifest so a reference edit
+  is visible as a reference change, not a prompt change.
+
+Reference content is repeated in every per-chunk prompt in the MVP. Per-slot or
+per-chunk inclusion policies are deferred until cost data justifies them.
+
+## Provenance
+
+The run manifest must record resolved references separately from source
+digests. For every bound lane and slot, it should record:
+
+- lane ID;
+- slot name;
+- origin type and URI;
+- content digest;
+- media type;
+- size in bytes;
+- whether the binding came from config or CLI override.
+
+Reference digests must participate in any idempotency/cache key alongside source
+digests, prompt hashes, schema versions, model, and parameters. Two runs that
+differ only in reference content must be distinguishable from the manifest
+alone.
+
+Diagnostics for a run should include the resolved binding set with digests, not
+full reference content, consistent with the existing redacted-effective-config
+pattern.
+
+## Validation and Guardrails
+
+### References Are Not Evidence
+
+The primary new failure mode is the model extracting facts from references
+rather than from the source input. For example, a roster may list a player
+character's known spells, and the model might emit a spell-cast artifact for a
+spell that was never cast in the session.
+
+Defenses, in priority order:
+
+1. **Structural.** `SourceRef` remains the only grounding mechanism and can only
+   reference source units. No contract change should make references
+   addressable as evidence.
+2. **Prompt discipline.** Module templates should frame references explicitly as
+   reference material, such as "use the roster to resolve speakers to
+   characters; extract only events that occur in the transcript."
+3. **Validator support.** The source-reference validator, or a sibling
+   deterministic validator, should warn when referenced source text does not
+   plausibly relate to the extracted fact. Severity should be `warn`, not
+   `fail`, because transcripts can use paraphrase, nicknames, and abbreviations.
+4. **Regression fixtures.** Tests should include a fixture in which a bound
+   roster mentions a spell that is never cast in the transcript, asserting no
+   artifact record is produced for it.
+
+### Size and Sanity Guardrails
+
+- MVP accepts UTF-8 text content only. Other media types should be rejected with
+  a clear error.
+- A slot-level `MaxBytes` value should be enforced when declared.
+- Empty bound files should produce a warning because they are likely user error.
+
+## Out of Scope
+
+- Token budgeting and model context-window management for references.
+- Non-file reference producers, including prior-run artifacts, derived
+  summaries, and entity registries.
+- Per-chunk or per-slot inclusion policies.
+- Structured or parsed references such as typed roster schemas. References are
+  opaque text handed to prompts.
+- Reference caching, preprocessing, summarization, embedding, or retrieval.
+- Making references addressable as evidence in any form.
+

docs/troubleshooting.md

@@ -177,6 +177,34 @@ Fix:
 
 Provider error messages are redacted for configured API key values.
 
+## Scene Chunking Failure
+
+Symptoms include:
+
+- `dnd scenes chunker`
+- `malformed structured output`
+- `boundary_caveats`
+- `start_unit_id`
+- `end_unit_id`
+- `gap`
+- `overlap`
+- `final scene`
+- `complete structured output`
+
+Fix:
+
+- Validate the pipeline configuration and confirm the input module provides a
+  transcript source when using `chunk: dnd/scenes`.
+- Confirm the LLM profile has a working OpenAI-compatible `base_url`, `model`,
+  and credentials.
+- Inspect retained diagnostics for the run error and resolved pipeline.
+- If the error names malformed structured output, retry with a model that
+  follows structured response schemas reliably.
+- If the error names `boundary_caveats`, check for blank or whitespace-only
+  caveat text in the scene response.
+- Scene boundaries must use exact source-unit IDs, cover the full source
+  document, be contiguous, and not overlap.
+
 ## Output Write Failure
 
 Symptoms include:

internal/cli/catalog.go

@@ -10,6 +10,7 @@ import (
 	"gitea.maximumdirect.net/eric/notarius/internal/framework/contracts"
 	"gitea.maximumdirect.net/eric/notarius/internal/framework/llm"
 	"gitea.maximumdirect.net/eric/notarius/internal/framework/pipeline"
+	"gitea.maximumdirect.net/eric/notarius/internal/modules/chunk/dnd/scenes"
 	"gitea.maximumdirect.net/eric/notarius/internal/modules/chunk/generic"
 	"gitea.maximumdirect.net/eric/notarius/internal/modules/extract/dnd/spells"
 	"gitea.maximumdirect.net/eric/notarius/internal/modules/input/seriatim"
@@ -34,6 +35,9 @@ func productionRegistries() (pipeline.Registries, error) {
 	if err := generic.Register(registries.Chunkers); err != nil {
 		return pipeline.Registries{}, fmt.Errorf("register generic chunker: %w", err)
 	}
+	if err := scenes.Register(registries.Chunkers); err != nil {
+		return pipeline.Registries{}, fmt.Errorf("register dnd scenes chunker: %w", err)
+	}
 	if err := spells.Register(registries.Extractors); err != nil {
 		return pipeline.Registries{}, fmt.Errorf("register dnd spells extractor: %w", err)
 	}

internal/cli/run_test.go

@@ -16,6 +16,7 @@ import (
 	"gitea.maximumdirect.net/eric/notarius/internal/core/diagnostics"
 	"gitea.maximumdirect.net/eric/notarius/internal/framework/contracts"
 	"gitea.maximumdirect.net/eric/notarius/internal/framework/pipeline"
+	"gitea.maximumdirect.net/eric/notarius/internal/modules/chunk/dnd/scenes"
 	"gitea.maximumdirect.net/eric/notarius/internal/modules/chunk/generic"
 	"gitea.maximumdirect.net/eric/notarius/internal/modules/extract/dnd/spells"
 	"gitea.maximumdirect.net/eric/notarius/internal/modules/input/seriatim"
@@ -136,6 +137,11 @@ func TestProductionCatalogIncludesDefaultModules(t *testing.T) {
 			got:  func() (pipeline.ModuleSpec, bool) { return catalog.Chunkers.Spec(generic.Key) },
 			want: generic.ModuleSpec(),
 		},
+		{
+			name: "dnd scenes chunker",
+			got:  func() (pipeline.ModuleSpec, bool) { return catalog.Chunkers.Spec(scenes.Key) },
+			want: scenes.ModuleSpec(),
+		},
 		{
 			name: "dnd spells extractor",
 			got:  func() (pipeline.ModuleSpec, bool) { return catalog.Extractors.Spec(spells.Key) },
@@ -186,6 +192,21 @@ func TestRunConfigValidateUsesProductionCatalogByDefault(t *testing.T) {
 	}
 }
 
+func TestRunConfigValidateAcceptsDNDScenesChunker(t *testing.T) {
+	configPath := writeTestConfig(t, mvpConfigYAMLWithChunk("dnd-session", scenes.Key, "dnd/spells"))
+	var stdout bytes.Buffer
+	var stderr bytes.Buffer
+
+	code := RunWithOptions([]string{"config", "validate", "--config", configPath, "--pipeline", "dnd-session"}, &stdout, &stderr, Options{})
+
+	if code != 0 {
+		t.Fatalf("RunWithOptions() code = %d, stderr=%q", code, stderr.String())
+	}
+	if !strings.Contains(stdout.String(), "is valid for pipeline") {
+		t.Fatalf("stdout = %q, want validation success", stdout.String())
+	}
+}
+
 func TestRunConfigValidateUnknownProductionModuleIncludesContext(t *testing.T) {
 	configPath := writeTestConfig(t, mvpConfigYAML("dnd-session", "missing/extract"))
 	var stdout bytes.Buffer
@@ -1041,6 +1062,81 @@ func TestExampleFixtureRunWritesExpectedJSON(t *testing.T) {
 	}
 }
 
+func TestExampleFixtureRunWithDNDScenesRecordsChunkerAndWarnings(t *testing.T) {
+	configPath := writeTestConfig(t, mvpConfigYAMLWithChunk("dnd-session", scenes.Key, "dnd/spells"))
+	inputPath := fixturePath(t, "examples/seriatim-minimal-transcript.json")
+	outputDir := t.TempDir()
+	diagnosticsDir := t.TempDir()
+	client := newSceneRunLLMClient("Scene boundary was ambiguous.")
+	var stdout bytes.Buffer
+	var stderr bytes.Buffer
+
+	code := RunWithOptions([]string{"run", "dnd-session", "--config", configPath, "--input", inputPath, "--output-dir", outputDir, "--diagnostics-dir", diagnosticsDir}, &stdout, &stderr, Options{
+		LLMClientFactory: fakeLLMFactory(client, nil),
+	})
+
+	if code != 0 {
+		t.Fatalf("RunWithOptions() code = %d, stderr=%q", code, stderr.String())
+	}
+	if client.calls != 2 {
+		t.Fatalf("LLM calls = %d, want chunking and extraction calls", client.calls)
+	}
+	if !strings.Contains(stderr.String(), "1 warning") {
+		t.Fatalf("stderr = %q, want warning count", stderr.String())
+	}
+
+	runOutputDir := onlyChildDir(t, outputDir)
+	manifestBytes := readFile(t, filepath.Join(runOutputDir, "manifest.json"))
+	var manifest artifacts.RunManifest
+	if err := json.Unmarshal(manifestBytes, &manifest); err != nil {
+		t.Fatalf("unmarshal manifest: %v", err)
+	}
+	if manifest.Chunker != scenes.Key {
+		t.Fatalf("manifest chunker = %q, want %q", manifest.Chunker, scenes.Key)
+	}
+	chunkerMetadata := manifest.ModuleMetadata["chunker"]
+	if chunkerMetadata == nil {
+		t.Fatalf("module metadata chunker = %#v, want object", manifest.ModuleMetadata["chunker"])
+	}
+	wantMetadataKeys := []string{
+		"prompt_id",
+		"prompt_version",
+		"prompt_sha256",
+		"response_schema_key",
+		"response_schema_id",
+		"response_schema_name",
+		"response_schema_version",
+		"response_schema_sha256",
+	}
+	if len(chunkerMetadata) != len(wantMetadataKeys) {
+		t.Fatalf("chunker metadata keys = %#v, want %d keys", chunkerMetadata, len(wantMetadataKeys))
+	}
+	for _, key := range wantMetadataKeys {
+		value, ok := chunkerMetadata[key]
+		if !ok {
+			t.Fatalf("chunker metadata missing key %q: %#v", key, chunkerMetadata)
+		}
+		if _, ok := value.(string); !ok {
+			t.Fatalf("chunker metadata[%q] = %#v, want string", key, value)
+		}
+	}
+	for _, forbidden := range []string{"prompt", "schema", "source", "text", "payload", "api_key", "secret", "token"} {
+		if _, ok := chunkerMetadata[forbidden]; ok {
+			t.Fatalf("chunker metadata leaked forbidden key %q: %#v", forbidden, chunkerMetadata)
+		}
+	}
+	for _, forbidden := range []string{"Source document ID:", "Aria casts Cure Wounds.", "spell_casts", "Scene boundary was ambiguous."} {
+		if strings.Contains(string(manifestBytes), forbidden) {
+			t.Fatalf("manifest leaked %q: %s", forbidden, manifestBytes)
+		}
+	}
+
+	warnings := string(readFile(t, filepath.Join(runOutputDir, "warnings.json")))
+	if !strings.Contains(warnings, "scene_boundary_caveat") || !strings.Contains(warnings, "Scene boundary was ambiguous.") {
+		t.Fatalf("warnings output = %s, want scene boundary caveat", warnings)
+	}
+}
+
 func TestExampleFixtureRunOnlySpells(t *testing.T) {
 	configPath := fixturePath(t, "examples/dnd-spells.config.yml")
 	inputPath := fixturePath(t, "examples/seriatim-minimal-transcript.json")
@@ -1220,6 +1316,18 @@ pipelines:
 `
 }
 
+func mvpConfigYAMLWithChunk(pipelineID string, chunker string, extractor string) string {
+	return `version: 1
+pipelines:
+  ` + pipelineID + `:
+    input: seriatim
+    chunk: ` + chunker + `
+    artifacts:
+      spells:
+        extract: ` + extractor + `
+`
+}
+
 func mvpConfigYAMLForLanes(pipelineID string, laneIDs ...string) string {
 	var b strings.Builder
 	b.WriteString("version: 1\n")
@@ -1287,6 +1395,7 @@ type fakeRunLLMClient struct {
 	calls            int
 	err              error
 	payload          map[string]any
+	sceneCaveat      string
 }
 
 func newFakeRunLLMClient(invalidSourceRef bool) *fakeRunLLMClient {
@@ -1301,11 +1410,43 @@ func newMalformedRunLLMClient() *fakeRunLLMClient {
 	return &fakeRunLLMClient{payload: map[string]any{}}
 }
 
+func newSceneRunLLMClient(caveat string) *fakeRunLLMClient {
+	return &fakeRunLLMClient{sceneCaveat: caveat}
+}
+
 func (client *fakeRunLLMClient) CompleteStructured(ctx context.Context, req contracts.StructuredCompletionRequest, out any) (contracts.StructuredCompletionResponse, error) {
 	client.calls++
 	if client.err != nil {
 		return contracts.StructuredCompletionResponse{}, client.err
 	}
+	if req.StageName == scenes.Key && client.payload == nil {
+		payload := map[string]any{
+			"scenes": []map[string]any{
+				{
+					"start_unit_id":       "seg-001",
+					"end_unit_id":         "seg-002",
+					"short_title":         "Opening spell",
+					"primary_mode":        "Narrative",
+					"main_participants":   []string{"Aria"},
+					"summary":             "Aria casts a spell.",
+					"boundary_note":       "The provided source units form one scene.",
+					"boundary_confidence": "High",
+				},
+			},
+			"boundary_caveats": []string{},
+		}
+		if client.sceneCaveat != "" {
+			payload["boundary_caveats"] = []string{client.sceneCaveat}
+		}
+		encoded, err := json.Marshal(payload)
+		if err != nil {
+			return contracts.StructuredCompletionResponse{}, err
+		}
+		if err := json.Unmarshal(encoded, out); err != nil {
+			return contracts.StructuredCompletionResponse{}, err
+		}
+		return contracts.StructuredCompletionResponse{Content: encoded}, nil
+	}
 	startUnitID := "seg-001"
 	if client.invalidSourceRef {
 		startUnitID = "missing-segment"

internal/core/artifacts/artifacts.go

@@ -59,6 +59,7 @@ type RunManifest struct {
 	Merger           string                    `json:"merger,omitempty"`
 	Normalizer       string                    `json:"normalizer,omitempty"`
 	OutputEncoder    string                    `json:"output_encoder,omitempty"`
+	ModuleMetadata   map[string]map[string]any `json:"module_metadata,omitempty"`
 	ArtifactLanes    []ArtifactLaneManifest    `json:"artifact_lanes,omitempty"`
 	LLMProfiles      []LLMProfileManifest      `json:"llm_profiles,omitempty"`
 	SchemaVersion    string                    `json:"schema_version,omitempty"`

internal/core/artifacts/artifacts_test.go

@@ -183,6 +183,42 @@ func TestRunManifestIncludesPipelineAndArtifactLaneFields(t *testing.T) {
 	assertHasKeys(t, lane, "id", "extractor", "merger", "normalizer", "validators", "metadata")
 }
 
+func TestRunManifestIncludesTopLevelModuleMetadata(t *testing.T) {
+	manifest := RunManifest{
+		ModuleMetadata: map[string]map[string]any{
+			"chunker": {
+				"prompt_id":            "dnd.scenes",
+				"prompt_version":       "v1",
+				"prompt_sha256":        "sha256:abc123",
+				"response_schema_key":  "dnd_scenes",
+				"response_schema_name": "dnd_scenes",
+			},
+		},
+	}
+
+	gotJSON, err := json.Marshal(manifest)
+	if err != nil {
+		t.Fatalf("json.Marshal() error = %v", err)
+	}
+
+	var got map[string]any
+	if err := json.Unmarshal(gotJSON, &got); err != nil {
+		t.Fatalf("json.Unmarshal() error = %v", err)
+	}
+
+	moduleMetadata, ok := got["module_metadata"].(map[string]any)
+	if !ok {
+		t.Fatalf("module_metadata = %#v, want object", got["module_metadata"])
+	}
+	assertHasKeys(t, moduleMetadata, "chunker")
+
+	chunkerMetadata, ok := moduleMetadata["chunker"].(map[string]any)
+	if !ok {
+		t.Fatalf("module_metadata.chunker = %#v, want object", moduleMetadata["chunker"])
+	}
+	assertHasKeys(t, chunkerMetadata, "prompt_id", "prompt_version", "prompt_sha256", "response_schema_key", "response_schema_name")
+}
+
 func assertHasKeys(t *testing.T, values map[string]any, keys ...string) {
 	t.Helper()
 

internal/core/config/effective_config_test.go

@@ -98,6 +98,43 @@ func TestResolveSurfacesMissingCapabilityThroughCatalog(t *testing.T) {
 	}
 }
 
+func TestResolveCanBindSceneChunkerFromCatalog(t *testing.T) {
+	cfg := validConfig()
+	profile := cfg.Pipelines["example"]
+	profile.Chunk = pipeline.Binding("dnd/scenes")
+	lane := profile.Artifacts["events"]
+	profile.Artifacts = map[string]pipeline.ArtifactLaneProfile{"events": lane}
+	cfg.Pipelines["example"] = profile
+
+	catalog := fakeCatalog(t,
+		pipeline.ModuleSpec{
+			Key:      "fake/input",
+			Stage:    pipeline.StageInput,
+			Provides: []string{"source.transcript"},
+		},
+		pipeline.ModuleSpec{
+			Key:      "fake/extract",
+			Stage:    pipeline.StageExtract,
+			Requires: []string{"chunks", "source.transcript"},
+			Provides: []string{"artifact"},
+		},
+	)
+	mustRegisterChunker(t, catalog.Chunkers, pipeline.ModuleSpec{
+		Key:      "dnd/scenes",
+		Stage:    pipeline.StageChunk,
+		Requires: []string{"source.transcript"},
+		Provides: []string{"chunks", "chunks.scenes"},
+	})
+
+	effective, err := cfg.Resolve(ResolveInput{PipelineID: "example", Catalog: catalog})
+	if err != nil {
+		t.Fatalf("Resolve() error = %v, want nil", err)
+	}
+	if got := effective.ResolvedPipeline.Chunk.Module; got != "dnd/scenes" {
+		t.Fatalf("Chunk.Module = %q, want dnd/scenes", got)
+	}
+}
+
 func TestResolveDigestChangesWhenEffectiveConfigChanges(t *testing.T) {
 	cfg := validConfig()
 	first, err := cfg.Resolve(ResolveInput{PipelineID: "example", Catalog: fakeCatalog(t)})

internal/framework/contracts/composition_test.go

@@ -17,6 +17,7 @@ var _ contracts.Extractor = compositionExtractor{}
 var _ contracts.Merger = compositionMerger{}
 var _ contracts.Normalizer = compositionNormalizer{}
 var _ contracts.Validator = compositionValidator{}
+var _ contracts.StructuredLLMClient = compositionLLMClient{}
 var _ contracts.OutputEncoder = compositionOutputEncoder{}
 
 func TestContractsComposeAcrossPackages(t *testing.T) {
@@ -39,6 +40,7 @@ func TestContractsComposeAcrossPackages(t *testing.T) {
 
 	chunking, err := chunker.Chunk(ctx, contracts.ChunkRequest{
 		Source:    doc,
+		LLMClient: compositionLLMClient{},
 		Metadata:  map[string]any{"max_units": 2},
 	})
 	if err != nil {
@@ -164,6 +166,9 @@ func (chunker compositionChunker) Chunk(ctx context.Context, req contracts.Chunk
 	if req.Source == nil {
 		return contracts.ChunkResult{}, errors.New("source document is required")
 	}
+	if req.LLMClient == nil {
+		return contracts.ChunkResult{}, errors.New("structured llm client is required")
+	}
 
 	return contracts.ChunkResult{
 		Chunks: []contracts.SourceChunk{
@@ -178,6 +183,12 @@ func (chunker compositionChunker) Chunk(ctx context.Context, req contracts.Chunk
 	}, nil
 }
 
+type compositionLLMClient struct{}
+
+func (client compositionLLMClient) CompleteStructured(ctx context.Context, req contracts.StructuredCompletionRequest, out any) (contracts.StructuredCompletionResponse, error) {
+	return contracts.StructuredCompletionResponse{}, nil
+}
+
 type compositionExtractor struct{}
 
 func (extractor compositionExtractor) Key() string {

internal/framework/contracts/contracts.go

@@ -58,6 +58,7 @@ type SourceChunk struct {
 
 type ChunkRequest struct {
 	Source     *source.SourceDocument `json:"-"`
+	LLMClient  StructuredLLMClient    `json:"-"`
 	LLMProfile string                 `json:"llm_profile,omitempty"`
 	Options    map[string]any         `json:"options,omitempty"`
 	Metadata   map[string]any         `json:"metadata,omitempty"`

internal/framework/contracts/contracts_test.go

@@ -117,6 +117,27 @@ func TestFakeChunkerReturnsSourceChunks(t *testing.T) {
 	}
 }
 
+func TestFakeChunkerReceivesLLMClient(t *testing.T) {
+	doc := &source.SourceDocument{
+		ID:     "source-1",
+		Kind:   "document",
+		Format: "text/plain",
+		Digest: "sha256:abc123",
+		Units: []source.SourceUnit{
+			{ID: "u1", Kind: "section", Text: "Source text."},
+		},
+	}
+	client := fakeLLMClient{}
+	chunker := &recordingChunker{key: "llm-chunker"}
+
+	if _, err := chunker.Chunk(context.Background(), ChunkRequest{Source: doc, LLMClient: client}); err != nil {
+		t.Fatalf("Chunk() error = %v, want nil", err)
+	}
+	if chunker.request.LLMClient == nil {
+		t.Fatal("ChunkRequest.LLMClient = nil, want structured LLM client")
+	}
+}
+
 func TestFakeExtractorReceivesChunkAndAmbientContext(t *testing.T) {
 	extractor := fakeExtractor{
 		key:           "generic-extractor",
@@ -305,6 +326,20 @@ func (chunker fakeChunker) Chunk(ctx context.Context, req ChunkRequest) (ChunkRe
 	}, nil
 }
 
+type recordingChunker struct {
+	key     string
+	request ChunkRequest
+}
+
+func (chunker *recordingChunker) Key() string {
+	return chunker.key
+}
+
+func (chunker *recordingChunker) Chunk(ctx context.Context, req ChunkRequest) (ChunkResult, error) {
+	chunker.request = req
+	return fakeChunker{key: chunker.key}.Chunk(ctx, req)
+}
+
 type fakeExtractor struct {
 	key           string
 	artifactType  string

internal/framework/pipeline/chunk_validation.go

@@ -0,0 +1,82 @@
+package pipeline
+
+import (
+	"fmt"
+	"strings"
+
+	"gitea.maximumdirect.net/eric/notarius/internal/core/source"
+	"gitea.maximumdirect.net/eric/notarius/internal/framework/contracts"
+)
+
+func validateAndCanonicalizeChunkResult(doc *source.SourceDocument, chunks []contracts.SourceChunk) ([]contracts.SourceChunk, error) {
+	sourceUnitIndexes := make(map[string]int, len(doc.Units))
+	sourceUnits := make(map[string]source.SourceUnit, len(doc.Units))
+	for index, unit := range doc.Units {
+		sourceUnitIndexes[unit.ID] = index
+		sourceUnits[unit.ID] = unit
+	}
+
+	canonicalChunks := make([]contracts.SourceChunk, 0, len(chunks))
+	seenChunkIDs := make(map[string]struct{}, len(chunks))
+	for chunkIndex, chunk := range chunks {
+		if strings.TrimSpace(chunk.ID) == "" {
+			return nil, fmt.Errorf("chunk[%d].id must not be empty", chunkIndex)
+		}
+		if _, ok := seenChunkIDs[chunk.ID]; ok {
+			return nil, fmt.Errorf("chunk id %q is duplicated", chunk.ID)
+		}
+		seenChunkIDs[chunk.ID] = struct{}{}
+
+		if chunk.SourceID != doc.ID {
+			return nil, fmt.Errorf("chunk %q source_id %q does not match source document id %q", chunk.ID, chunk.SourceID, doc.ID)
+		}
+		if chunk.Index != chunkIndex {
+			return nil, fmt.Errorf("chunk %q index %d does not match returned order %d", chunk.ID, chunk.Index, chunkIndex)
+		}
+		if len(chunk.Units) == 0 {
+			return nil, fmt.Errorf("chunk %q units must not be empty", chunk.ID)
+		}
+
+		seenUnitIDs := make(map[string]struct{}, len(chunk.Units))
+		previousSourceIndex := -1
+		canonicalUnits := make([]source.SourceUnit, 0, len(chunk.Units))
+		for unitIndex, unit := range chunk.Units {
+			if strings.TrimSpace(unit.ID) == "" {
+				return nil, fmt.Errorf("chunk %q unit[%d].id must not be empty", chunk.ID, unitIndex)
+			}
+			if _, ok := seenUnitIDs[unit.ID]; ok {
+				return nil, fmt.Errorf("chunk %q repeats source unit %q", chunk.ID, unit.ID)
+			}
+			seenUnitIDs[unit.ID] = struct{}{}
+
+			sourceIndex, ok := sourceUnitIndexes[unit.ID]
+			if !ok {
+				return nil, fmt.Errorf("chunk %q source unit %q was not found in source document %q", chunk.ID, unit.ID, doc.ID)
+			}
+			if sourceIndex <= previousSourceIndex {
+				return nil, fmt.Errorf("chunk %q source units must appear in source document order", chunk.ID)
+			}
+			previousSourceIndex = sourceIndex
+			canonicalUnits = append(canonicalUnits, cloneSourceUnit(sourceUnits[unit.ID]))
+		}
+
+		canonicalChunks = append(canonicalChunks, contracts.SourceChunk{
+			ID:       chunk.ID,
+			SourceID: chunk.SourceID,
+			Index:    chunk.Index,
+			Units:    canonicalUnits,
+			Metadata: cloneMetadata(chunk.Metadata),
+		})
+	}
+
+	return canonicalChunks, nil
+}
+
+func cloneSourceUnit(unit source.SourceUnit) source.SourceUnit {
+	return source.SourceUnit{
+		ID:       unit.ID,
+		Kind:     unit.Kind,
+		Text:     unit.Text,
+		Metadata: cloneMetadata(unit.Metadata),
+	}
+}

internal/framework/pipeline/runner.go

@@ -69,6 +69,7 @@ func (r *Runner) Run(ctx context.Context, input RunInput) (RunOutput, error) {
 	if err != nil {
 		return failOutput(output), fmt.Errorf("build input adapter %q: %w", input.Pipeline.Input.Module, err)
 	}
+	attachModuleManifestMetadata(&output, "input", adapter)
 	doc, err := adapter.Parse(ctx, contracts.ParseRequest{
 		SourceID:   input.SourceID,
 		Path:       input.Path,
@@ -89,8 +90,10 @@ func (r *Runner) Run(ctx context.Context, input RunInput) (RunOutput, error) {
 	if err != nil {
 		return failOutput(output), fmt.Errorf("build chunker %q: %w", input.Pipeline.Chunk.Module, err)
 	}
+	attachModuleManifestMetadata(&output, "chunker", chunker)
 	chunkResult, err := chunker.Chunk(ctx, contracts.ChunkRequest{
 		Source:     doc,
+		LLMClient:  input.LLMClient,
 		LLMProfile: input.Pipeline.Chunk.LLMProfile,
 		Options:    cloneOptions(input.Pipeline.Chunk.Options),
 		Metadata:   input.Metadata,
@@ -102,10 +105,14 @@ func (r *Runner) Run(ctx context.Context, input RunInput) (RunOutput, error) {
 	if len(chunkResult.Chunks) == 0 {
 		return failOutput(output), fmt.Errorf("chunker %q returned no chunks", chunker.Key())
 	}
+	canonicalChunks, err := validateAndCanonicalizeChunkResult(doc, chunkResult.Chunks)
+	if err != nil {
+		return failOutput(output), fmt.Errorf("validate chunks from chunker %q: %w", chunker.Key(), err)
+	}
 
 	nextCandidateIndex := 0
 	for _, lane := range input.Pipeline.ArtifactLanes {
-		if err := r.runLane(ctx, input, doc, chunkResult.Chunks, lane, &output, &nextCandidateIndex); err != nil {
+		if err := r.runLane(ctx, input, doc, canonicalChunks, lane, &output, &nextCandidateIndex); err != nil {
 			return failOutput(output), err
 		}
 	}
@@ -121,6 +128,7 @@ func (r *Runner) Run(ctx context.Context, input RunInput) (RunOutput, error) {
 	if err != nil {
 		return failOutput(output), fmt.Errorf("build output encoder %q: %w", input.Pipeline.Output.Module, err)
 	}
+	attachModuleManifestMetadata(&output, "output", encoder)
 	encoded, err := encoder.Encode(ctx, contracts.OutputRequest{
 		Manifest:   output.Manifest,
 		Approved:   output.Approved,
@@ -382,14 +390,10 @@ func setLaneManifestMetadata(output *RunOutput, laneID string, modules ...any) {
 
 		metadata := make(map[string]any)
 		for _, module := range modules {
-			provider, ok := module.(contracts.ManifestMetadataProvider)
+			moduleMetadata, ok := moduleManifestMetadata(module)
 			if !ok {
 				continue
 			}
-			moduleMetadata := cloneMetadata(provider.ManifestMetadata())
-			if len(moduleMetadata) == 0 {
-				continue
-			}
 			key := manifestMetadataKey(module)
 			if key == "" {
 				continue
@@ -403,6 +407,20 @@ func setLaneManifestMetadata(output *RunOutput, laneID string, modules ...any) {
 	}
 }
 
+func attachModuleManifestMetadata(output *RunOutput, moduleKey string, module any) {
+	if output == nil {
+		return
+	}
+	moduleMetadata, ok := moduleManifestMetadata(module)
+	if !ok {
+		return
+	}
+	if output.Manifest.ModuleMetadata == nil {
+		output.Manifest.ModuleMetadata = make(map[string]map[string]any)
+	}
+	output.Manifest.ModuleMetadata[moduleKey] = moduleMetadata
+}
+
 func manifestMetadataKey(module any) string {
 	switch module.(type) {
 	case contracts.Extractor:
@@ -416,6 +434,19 @@ func manifestMetadataKey(module any) string {
 	}
 }
 
+func moduleManifestMetadata(module any) (map[string]any, bool) {
+	provider, ok := module.(contracts.ManifestMetadataProvider)
+	if !ok {
+		return nil, false
+	}
+
+	moduleMetadata := cloneMetadata(provider.ManifestMetadata())
+	if len(moduleMetadata) == 0 {
+		return nil, false
+	}
+	return moduleMetadata, true
+}
+
 func outputFilesFromResult(result contracts.OutputResult) ([]contracts.OutputFile, error) {
 	out := make([]contracts.OutputFile, 0, len(result.Files))
 	for _, file := range result.Files {

internal/framework/pipeline/runner_test.go

@@ -256,6 +256,191 @@ func TestRunRejectsChunkerBuildChunkAndEmptyChunkErrors(t *testing.T) {
 	}
 }
 
+func TestRunRejectsInvalidChunks(t *testing.T) {
+	tests := []struct {
+		name   string
+		chunks []contracts.SourceChunk
+		want   string
+	}{
+		{
+			name:   "empty chunk id",
+			chunks: []contracts.SourceChunk{{ID: "", SourceID: "source-1", Index: 0, Units: []source.SourceUnit{unitWithID("u1")}}},
+			want:   "id must not be empty",
+		},
+		{
+			name: "duplicate chunk id",
+			chunks: []contracts.SourceChunk{
+				{ID: "chunk-0", SourceID: "source-1", Index: 0, Units: []source.SourceUnit{unitWithID("u1")}},
+				{ID: "chunk-0", SourceID: "source-1", Index: 1, Units: []source.SourceUnit{unitWithID("u2")}},
+			},
+			want: "duplicated",
+		},
+		{
+			name:   "wrong source id",
+			chunks: []contracts.SourceChunk{{ID: "chunk-0", SourceID: "other-source", Index: 0, Units: []source.SourceUnit{unitWithID("u1")}}},
+			want:   "source_id",
+		},
+		{
+			name:   "wrong index",
+			chunks: []contracts.SourceChunk{{ID: "chunk-0", SourceID: "source-1", Index: 1, Units: []source.SourceUnit{unitWithID("u1")}}},
+			want:   "index",
+		},
+		{
+			name:   "empty units",
+			chunks: []contracts.SourceChunk{{ID: "chunk-0", SourceID: "source-1", Index: 0}},
+			want:   "units must not be empty",
+		},
+		{
+			name:   "repeated unit inside chunk",
+			chunks: []contracts.SourceChunk{{ID: "chunk-0", SourceID: "source-1", Index: 0, Units: []source.SourceUnit{unitWithID("u1"), unitWithID("u1")}}},
+			want:   "repeats source unit",
+		},
+		{
+			name:   "unknown unit",
+			chunks: []contracts.SourceChunk{{ID: "chunk-0", SourceID: "source-1", Index: 0, Units: []source.SourceUnit{unitWithID("u9")}}},
+			want:   "was not found",
+		},
+		{
+			name:   "units out of source order",
+			chunks: []contracts.SourceChunk{{ID: "chunk-0", SourceID: "source-1", Index: 0, Units: []source.SourceUnit{unitWithID("u2"), unitWithID("u1")}}},
+			want:   "source document order",
+		},
+	}
+
+	for _, test := range tests {
+		t.Run(test.name, func(t *testing.T) {
+			modules := defaultRunnerModules()
+			modules.chunker.chunks = test.chunks
+
+			output, err := New(newRunnerRegistries(t, modules)).Run(context.Background(), RunInput{Pipeline: resolvedPipeline()})
+
+			assertRunError(t, err, test.want)
+			if output.Manifest.ValidationStatus != "failed" {
+				t.Fatalf("ValidationStatus = %q, want failed", output.Manifest.ValidationStatus)
+			}
+			if len(modules.extractors["extract-alpha"].requests) != 0 {
+				t.Fatalf("extractor calls = %d, want none after invalid chunks", len(modules.extractors["extract-alpha"].requests))
+			}
+		})
+	}
+}
+
+func TestRunAllowsPartialCoverageAndOverlappingChunks(t *testing.T) {
+	modules := defaultRunnerModules()
+	modules.chunker.chunks = []contracts.SourceChunk{
+		{ID: "chunk-0", SourceID: "source-1", Index: 0, Units: []source.SourceUnit{unitWithID("u1"), unitWithID("u2")}},
+		{ID: "chunk-1", SourceID: "source-1", Index: 1, Units: []source.SourceUnit{unitWithID("u2")}},
+	}
+
+	output, err := New(newRunnerRegistries(t, modules)).Run(context.Background(), RunInput{Pipeline: resolvedPipeline()})
+	if err != nil {
+		t.Fatalf("Run() error = %v, want nil", err)
+	}
+	if len(output.Approved) != 2 {
+		t.Fatalf("len(Approved) = %d, want one candidate per accepted chunk", len(output.Approved))
+	}
+}
+
+func TestRunCanonicalizesChunkUnitsBeforeExtraction(t *testing.T) {
+	modules := defaultRunnerModules()
+	modules.input.doc = sourceDocumentWithUnitMetadata()
+	modules.chunker.chunks = []contracts.SourceChunk{
+		{
+			ID:       "chunk-0",
+			SourceID: "source-1",
+			Index:    0,
+			Units: []source.SourceUnit{
+				{
+					ID:   "u1",
+					Kind: "mutated-kind",
+					Text: "mutated text",
+					Metadata: map[string]any{
+						"speaker": "chunker-speaker",
+						"note":    "chunker note",
+					},
+				},
+			},
+		},
+	}
+
+	output, err := New(newRunnerRegistries(t, modules)).Run(context.Background(), RunInput{Pipeline: resolvedPipeline()})
+	if err != nil {
+		t.Fatalf("Run() error = %v, want nil", err)
+	}
+
+	if len(output.Approved) != 1 {
+		t.Fatalf("len(Approved) = %d, want 1", len(output.Approved))
+	}
+
+	extractor := modules.extractors["extract-alpha"]
+	if len(extractor.requests) != 1 {
+		t.Fatalf("len(extractor requests) = %d, want 1", len(extractor.requests))
+	}
+	chunk := extractor.requests[0].Chunk
+	if chunk == nil {
+		t.Fatal("extractor chunk = nil, want canonical chunk")
+	}
+	if chunk.Units[0].ID != "u1" || chunk.Units[0].Kind != "source-kind" || chunk.Units[0].Text != "source text" {
+		t.Fatalf("chunk unit = %#v, want source document unit values", chunk.Units[0])
+	}
+	if got := chunk.Units[0].Metadata["speaker"]; got != "source-speaker" {
+		t.Fatalf("chunk unit metadata = %#v, want source document metadata", chunk.Units[0].Metadata)
+	}
+	if got := chunk.Units[0].Metadata["topic"]; got != "source-topic" {
+		t.Fatalf("chunk unit metadata = %#v, want cloned source document metadata", chunk.Units[0].Metadata)
+	}
+
+	modules.input.doc.Units[0].Kind = "changed-kind"
+	modules.input.doc.Units[0].Text = "changed text"
+	modules.input.doc.Units[0].Metadata["speaker"] = "changed-speaker"
+	if chunk.Units[0].Kind != "source-kind" || chunk.Units[0].Text != "source text" || chunk.Units[0].Metadata["speaker"] != "source-speaker" {
+		t.Fatalf("chunk unit changed after source mutation: %#v", chunk.Units[0])
+	}
+}
+
+func TestRunPreservesChunkMetadataDuringCanonicalization(t *testing.T) {
+	modules := defaultRunnerModules()
+	modules.chunker.chunks = []contracts.SourceChunk{
+		{
+			ID:       "chunk-0",
+			SourceID: "source-1",
+			Index:    0,
+			Units: []source.SourceUnit{
+				unitWithID("u1"),
+			},
+			Metadata: map[string]any{
+				"scene_title":   "Original scene",
+				"boundary_note": "Chunker note",
+			},
+		},
+	}
+
+	_, err := New(newRunnerRegistries(t, modules)).Run(context.Background(), RunInput{Pipeline: resolvedPipeline()})
+	if err != nil {
+		t.Fatalf("Run() error = %v, want nil", err)
+	}
+
+	extractor := modules.extractors["extract-alpha"]
+	if len(extractor.requests) != 1 || extractor.requests[0].Chunk == nil {
+		t.Fatalf("extractor requests = %#v, want one canonical chunk", extractor.requests)
+	}
+	if got := extractor.requests[0].Chunk.Metadata["scene_title"]; got != "Original scene" {
+		t.Fatalf("chunk metadata = %#v, want chunker metadata", extractor.requests[0].Chunk.Metadata)
+	}
+	if got := extractor.requests[0].Chunk.Metadata["boundary_note"]; got != "Chunker note" {
+		t.Fatalf("chunk metadata = %#v, want chunker metadata", extractor.requests[0].Chunk.Metadata)
+	}
+
+	modules.chunker.chunks[0].Metadata["scene_title"] = "changed"
+	modules.chunker.chunks[0].Metadata["boundary_note"] = "changed"
+	if got := extractor.requests[0].Chunk.Metadata["scene_title"]; got != "Original scene" {
+		t.Fatalf("chunk metadata aliased to chunker map: %#v", extractor.requests[0].Chunk.Metadata)
+	}
+	if got := extractor.requests[0].Chunk.Metadata["boundary_note"]; got != "Chunker note" {
+		t.Fatalf("chunk metadata aliased to chunker map: %#v", extractor.requests[0].Chunk.Metadata)
+	}
+}
+
 func TestRunExecutesChunksAndPassesChunkAndLLMClient(t *testing.T) {
 	modules := defaultRunnerModules()
 	llmClient := fakeLLMClient{}
@@ -273,6 +458,9 @@ func TestRunExecutesChunksAndPassesChunkAndLLMClient(t *testing.T) {
 	if !reflect.DeepEqual(extractor.seenChunkIDs, []string{"chunk-0", "chunk-1"}) {
 		t.Fatalf("seen chunks = %#v, want both chunks", extractor.seenChunkIDs)
 	}
+	if len(modules.chunker.requests) != 1 || modules.chunker.requests[0].LLMClient == nil {
+		t.Fatalf("chunker LLM client = %#v, want client on chunk request", modules.chunker.requests)
+	}
 	if len(extractor.seenLLMClients) != 2 || extractor.seenLLMClients[0] == nil || extractor.seenLLMClients[1] == nil {
 		t.Fatalf("seen LLM clients = %#v, want client for each chunk", extractor.seenLLMClients)
 	}
@@ -371,6 +559,47 @@ func TestRunPassesModuleBindingConfigToStageRequests(t *testing.T) {
 	}
 }
 
+func TestRunRecordsTopLevelModuleMetadataForSingletonModules(t *testing.T) {
+	modules := defaultRunnerModules()
+	modules.input.manifestMetadata = map[string]any{
+		"input_profile": "input-metadata",
+	}
+	modules.chunker.manifestMetadata = map[string]any{
+		"prompt_id":            "dnd.scenes",
+		"prompt_version":       "v1",
+		"prompt_sha256":        "sha256:chunker-prompt",
+		"response_schema_key":  "dnd_scenes",
+		"response_schema_id":   "schema-dnd-scenes",
+		"response_schema_name": "dnd_scenes",
+	}
+	modules.output.manifestMetadata = map[string]any{
+		"output_profile": "output-metadata",
+	}
+
+	output, err := New(newRunnerRegistries(t, modules)).Run(context.Background(), RunInput{Pipeline: resolvedPipeline()})
+	if err != nil {
+		t.Fatalf("Run() error = %v, want nil", err)
+	}
+
+	if output.Manifest.ModuleMetadata == nil {
+		t.Fatal("ModuleMetadata = nil, want module metadata map")
+	}
+	if got := output.Manifest.ModuleMetadata["input"]; !reflect.DeepEqual(got, modules.input.manifestMetadata) {
+		t.Fatalf("input module metadata = %#v, want %#v", got, modules.input.manifestMetadata)
+	}
+	if got := output.Manifest.ModuleMetadata["chunker"]; !reflect.DeepEqual(got, modules.chunker.manifestMetadata) {
+		t.Fatalf("chunker module metadata = %#v, want %#v", got, modules.chunker.manifestMetadata)
+	}
+	if got := output.Manifest.ModuleMetadata["output"]; !reflect.DeepEqual(got, modules.output.manifestMetadata) {
+		t.Fatalf("output module metadata = %#v, want %#v", got, modules.output.manifestMetadata)
+	}
+
+	modules.chunker.manifestMetadata["prompt_id"] = "changed"
+	if output.Manifest.ModuleMetadata["chunker"]["prompt_id"] != "dnd.scenes" {
+		t.Fatalf("chunker module metadata aliased to provider map: %#v", output.Manifest.ModuleMetadata["chunker"])
+	}
+}
+
 func TestRunPassesPerChunkCandidatesToMergeAndNormalize(t *testing.T) {
 	modules := defaultRunnerModules()
 
@@ -775,6 +1004,11 @@ func TestRunManifestIncludesExtractorMetadata(t *testing.T) {
 	if extractorMetadata["prompt_id"] != "test.prompt" || extractorMetadata["response_schema_name"] != "test_schema" {
 		t.Fatalf("extractor metadata = %#v, want prompt and schema metadata", extractorMetadata)
 	}
+	if output.Manifest.ModuleMetadata != nil {
+		if _, ok := output.Manifest.ModuleMetadata["extractor"]; ok {
+			t.Fatalf("top-level module metadata includes lane metadata key: %#v", output.Manifest.ModuleMetadata)
+		}
+	}
 }
 
 func TestRunReturnsPartialOutputWhenLaterLaneFails(t *testing.T) {
@@ -966,6 +1200,7 @@ type runnerInputAdapter struct {
 	key              string
 	doc              *source.SourceDocument
 	err              error
+	manifestMetadata map[string]any
 	requests         []contracts.ParseRequest
 }
 
@@ -978,11 +1213,16 @@ func (adapter *runnerInputAdapter) Parse(ctx context.Context, req contracts.Pars
 	return adapter.doc, adapter.err
 }
 
+func (adapter *runnerInputAdapter) ManifestMetadata() map[string]any {
+	return adapter.manifestMetadata
+}
+
 type runnerChunker struct {
 	key              string
 	chunks           []contracts.SourceChunk
 	warnings         []contracts.Warning
 	err              error
+	manifestMetadata map[string]any
 	requests         []contracts.ChunkRequest
 }
 
@@ -998,6 +1238,10 @@ func (chunker *runnerChunker) Chunk(ctx context.Context, req contracts.ChunkRequ
 	}, chunker.err
 }
 
+func (chunker *runnerChunker) ManifestMetadata() map[string]any {
+	return chunker.manifestMetadata
+}
+
 type runnerExtractor struct {
 	key              string
 	artifactType     string
@@ -1142,6 +1386,7 @@ type runnerOutputEncoder struct {
 	files            []contracts.OutputFile
 	warnings         []contracts.Warning
 	err              error
+	manifestMetadata map[string]any
 	requests         []contracts.OutputRequest
 }
 
@@ -1157,6 +1402,10 @@ func (encoder *runnerOutputEncoder) Encode(ctx context.Context, req contracts.Ou
 	}, encoder.err
 }
 
+func (encoder *runnerOutputEncoder) ManifestMetadata() map[string]any {
+	return encoder.manifestMetadata
+}
+
 type fakeLLMClient struct{}
 
 func (client fakeLLMClient) CompleteStructured(ctx context.Context, req contracts.StructuredCompletionRequest, out any) (contracts.StructuredCompletionResponse, error) {
@@ -1179,6 +1428,36 @@ func validSourceDocument() *source.SourceDocument {
 		Digest: "sha256:source",
 		Units: []source.SourceUnit{
 			{ID: "u1", Kind: "unit", Text: "Source unit."},
+			{ID: "u2", Kind: "unit", Text: "Second source unit."},
+			{ID: "u3", Kind: "unit", Text: "Third source unit."},
+		},
+	}
+}
+
+func sourceDocumentWithUnitMetadata() *source.SourceDocument {
+	return &source.SourceDocument{
+		ID:     "source-1",
+		Kind:   "document",
+		Format: "text/plain",
+		Digest: "sha256:source",
+		Units: []source.SourceUnit{
+			{
+				ID:   "u1",
+				Kind: "source-kind",
+				Text: "source text",
+				Metadata: map[string]any{
+					"speaker": "source-speaker",
+					"topic":   "source-topic",
+				},
+			},
+			{
+				ID:   "u2",
+				Kind: "source-kind",
+				Text: "second source text",
+				Metadata: map[string]any{
+					"speaker": "source-speaker-2",
+				},
+			},
 		},
 	}
 }
@@ -1194,6 +1473,19 @@ func sourceChunkWithID(id string, index int) contracts.SourceChunk {
 	}
 }
 
+func unitWithID(id string) source.SourceUnit {
+	switch id {
+	case "u1":
+		return source.SourceUnit{ID: "u1", Kind: "unit", Text: "Source unit."}
+	case "u2":
+		return source.SourceUnit{ID: "u2", Kind: "unit", Text: "Second source unit."}
+	case "u3":
+		return source.SourceUnit{ID: "u3", Kind: "unit", Text: "Third source unit."}
+	default:
+		return source.SourceUnit{ID: id, Kind: "unit", Text: "Unknown source unit."}
+	}
+}
+
 func warningReasons(warnings []contracts.Warning) []string {
 	reasons := make([]string, 0, len(warnings))
 	for _, warning := range warnings {

internal/modules/chunk/dnd/scenes/assets.go

@@ -0,0 +1,6 @@
+package scenes
+
+import "embed"
+
+//go:embed assets/prompts/*.md assets/schemas/*.json
+var embeddedAssets embed.FS

internal/modules/chunk/dnd/scenes/assets/prompts/system.md

@@ -0,0 +1,9 @@
+You identify coherent scenes in Dungeons & Dragons session source units.
+
+{{ hardening }}
+
+Use only the provided source units. Source text may contain transcription
+errors, repeated lines, incomplete sentences, and misheard proper nouns. Speaker
+metadata, when present, may be treated as accurate.
+
+Return only valid JSON matching the provided response schema.

internal/modules/chunk/dnd/scenes/assets/prompts/user.md

@@ -0,0 +1,71 @@
+Source document ID: {{ .SourceID }}
+
+Ordered source units:
+{{ range .Units }}
+- Unit ID: {{ .ID }}
+  Text: {{ .Text }}
+{{ if .Metadata }}
+  Metadata:
+{{ range .Metadata }}
+  - {{ .Key }}: {{ .Value }}
+{{ end }}
+{{ end }}
+{{ end }}
+
+Divide these source units into D&D scenes for the dnd/scenes chunk module.
+
+A scene is a coherent unit of play. Start a new scene when there is a meaningful
+change in location, objective, threat, activity, encounter, or mode of play.
+
+Good reasons to start a new scene include:
+- the party moves to a new location;
+- a combat encounter begins or ends;
+- combat changes into a substantially different phase;
+- the party shifts between combat, exploration, social interaction, discussion,
+  planning, travel, rest, or downtime;
+- a new NPC, faction, threat, or objective becomes central;
+- the party completes one immediate goal and begins another;
+- a major table-level rules discussion interrupts and materially changes play.
+
+Do not start a new scene merely because:
+- the speaker changes;
+- a new combat round begins;
+- a player asks a brief rules question;
+- there is a joke, aside, or short table comment;
+- a character takes a routine turn;
+- the same encounter continues without a meaningful change in situation.
+
+dnd/scenes boundary policy:
+- cover the full provided source document from the first source unit to the last
+  source unit;
+- return sequential scenes with no gaps;
+- do not overlap scenes;
+- preserve source-unit order;
+- use exact source-unit IDs from the ordered source units;
+- each scene must have start_unit_id and end_unit_id;
+- do not include final chunk IDs or chunk indexes.
+
+For each scene:
+- short_title should be brief and factual;
+- primary_mode must be Recap, Discussion, Combat, or Narrative;
+- main_participants should include only principal characters, NPCs, factions, or
+  groups involved;
+- summary should be factual and compact, usually one to three sentences;
+- boundary_note should explain why the scene begins at start_unit_id and ends at
+  end_unit_id;
+- boundary_confidence must be High, Medium, or Low.
+
+Primary mode guidance:
+- Use Recap for opening recap, initiative setup, session framing, or immediate
+  continuation from prior events.
+- Use Discussion when the party is primarily discussing options or choosing a
+  course of action.
+- Use Combat when active combat or combat-resolution mechanics dominate.
+- Use Narrative for all other non-combat gameplay, including exploration, social
+  interactions, shopping, preparation, travel, rest, and downtime.
+
+In boundary_caveats, list overall caveats about scene divisions. Include scenes
+that could reasonably be split differently, combat phases that were kept
+together, gradual transitions, or places where map context would have helped.
+
+Return exactly one JSON object and no explanatory text.

internal/modules/chunk/dnd/scenes/assets/schemas/dnd_scenes.v1.json

@@ -0,0 +1,84 @@
+{
+  "$schema": "https://json-schema.org/draft/2020-12/schema",
+  "$id": "notarius.dnd.scenes",
+  "type": "object",
+  "additionalProperties": false,
+  "required": [
+    "scenes",
+    "boundary_caveats"
+  ],
+  "properties": {
+    "scenes": {
+      "type": "array",
+      "minItems": 1,
+      "items": {
+        "type": "object",
+        "additionalProperties": false,
+        "required": [
+          "start_unit_id",
+          "end_unit_id",
+          "short_title",
+          "primary_mode",
+          "main_participants",
+          "summary",
+          "boundary_note",
+          "boundary_confidence"
+        ],
+        "properties": {
+          "start_unit_id": {
+            "type": "string",
+            "minLength": 1
+          },
+          "end_unit_id": {
+            "type": "string",
+            "minLength": 1
+          },
+          "short_title": {
+            "type": "string",
+            "minLength": 1
+          },
+          "primary_mode": {
+            "type": "string",
+            "enum": [
+              "Recap",
+              "Discussion",
+              "Combat",
+              "Narrative"
+            ]
+          },
+          "main_participants": {
+            "type": "array",
+            "minItems": 1,
+            "items": {
+              "type": "string",
+              "minLength": 1
+            }
+          },
+          "summary": {
+            "type": "string",
+            "minLength": 1
+          },
+          "boundary_note": {
+            "type": "string",
+            "minLength": 1
+          },
+          "boundary_confidence": {
+            "type": "string",
+            "enum": [
+              "High",
+              "Medium",
+              "Low"
+            ]
+          }
+        }
+      }
+    },
+    "boundary_caveats": {
+      "type": "array",
+      "items": {
+        "type": "string",
+        "minLength": 1
+      }
+    }
+  }
+}

internal/modules/chunk/dnd/scenes/chunker.go

@@ -0,0 +1,311 @@
+package scenes
+
+import (
+	"context"
+	"fmt"
+	"strings"
+
+	"gitea.maximumdirect.net/eric/notarius/internal/core/source"
+	"gitea.maximumdirect.net/eric/notarius/internal/framework/contracts"
+	"gitea.maximumdirect.net/eric/notarius/internal/framework/pipeline"
+)
+
+const Key = "dnd/scenes"
+
+var requiredCapabilities = []string{
+	"source.transcript",
+}
+
+var providedCapabilities = []string{
+	"chunks",
+	"chunks.scenes",
+}
+
+var _ contracts.Chunker = (*Chunker)(nil)
+var _ contracts.ManifestMetadataProvider = (*Chunker)(nil)
+
+type Chunker struct{}
+
+func New() *Chunker {
+	return &Chunker{}
+}
+
+func (c *Chunker) Key() string {
+	return Key
+}
+
+func (c *Chunker) ManifestMetadata() map[string]any {
+	promptMetadata := scenesPromptBundle.Metadata()
+	metadata := map[string]any{
+		"prompt_id":            PromptID,
+		"prompt_version":       promptMetadata.PromptVersion,
+		"prompt_sha256":        promptMetadata.SHA256,
+		"response_schema_key":  string(ResponseSchemaKey),
+		"response_schema_id":   ResponseSchemaID,
+		"response_schema_name": ResponseSchemaName,
+	}
+	if schema, err := loadResponseSchema(); err == nil {
+		metadata["response_schema_version"] = schema.Version
+		metadata["response_schema_sha256"] = schema.SHA256
+	}
+	return metadata
+}
+
+func (c *Chunker) Chunk(ctx context.Context, req contracts.ChunkRequest) (contracts.ChunkResult, error) {
+	if c == nil {
+		return contracts.ChunkResult{}, chunkerErrorf("chunker must not be nil")
+	}
+	if ctx == nil {
+		return contracts.ChunkResult{}, chunkerErrorf("context must not be nil")
+	}
+	if err := ctx.Err(); err != nil {
+		return contracts.ChunkResult{}, chunkerErrorf("context error before chunking: %w", err)
+	}
+	if req.Source == nil {
+		return contracts.ChunkResult{}, chunkerErrorf("source must not be nil")
+	}
+	if len(req.Source.Units) == 0 {
+		return contracts.ChunkResult{}, chunkerErrorf("source units must not be empty")
+	}
+	if err := source.ValidateDocument(req.Source); err != nil {
+		return contracts.ChunkResult{}, chunkerErrorf("validate source document: %w", err)
+	}
+	if req.LLMClient == nil {
+		return contracts.ChunkResult{}, chunkerErrorf("LLM client must not be nil")
+	}
+	if len(req.Options) > 0 {
+		return contracts.ChunkResult{}, chunkerErrorf("options are not supported")
+	}
+
+	system, user, _, err := renderPrompt(req)
+	if err != nil {
+		return contracts.ChunkResult{}, chunkerErrorf("render prompt: %w", err)
+	}
+	schema, err := loadResponseSchema()
+	if err != nil {
+		return contracts.ChunkResult{}, chunkerErrorf("load response schema %q: %w", ResponseSchemaKey, err)
+	}
+
+	var response chunkResponse
+	if _, err := req.LLMClient.CompleteStructured(ctx, contracts.StructuredCompletionRequest{
+		StageName: Key,
+		Messages: []contracts.LLMMessage{
+			{Role: "system", Content: system},
+			{Role: "user", Content: user},
+		},
+		ResponseSchemaName: schema.Name,
+		ResponseSchema:     schema.JSONSchema,
+	}, &response); err != nil {
+		return contracts.ChunkResult{}, chunkerErrorf("complete structured output: %w", err)
+	}
+
+	warnings, err := warningsFromCaveats(response.BoundaryCaveats)
+	if err != nil {
+		return contracts.ChunkResult{}, chunkerErrorf("malformed structured output: %w", err)
+	}
+	chunks, err := chunksFromResponse(req.Source, response)
+	if err != nil {
+		return contracts.ChunkResult{}, chunkerErrorf("malformed structured output: %w", err)
+	}
+	return contracts.ChunkResult{
+		Chunks:   chunks,
+		Warnings: warnings,
+	}, nil
+}
+
+func ModuleSpec() pipeline.ModuleSpec {
+	return pipeline.ModuleSpec{
+		Key:      Key,
+		Stage:    pipeline.StageChunk,
+		Requires: append([]string(nil), requiredCapabilities...),
+		Provides: append([]string(nil), providedCapabilities...),
+	}
+}
+
+func Register(registry *pipeline.ChunkerRegistry) error {
+	return registry.RegisterWithSpec(ModuleSpec(), func() (contracts.Chunker, error) {
+		return New(), nil
+	})
+}
+
+func chunksFromResponse(doc *source.SourceDocument, response chunkResponse) ([]contracts.SourceChunk, error) {
+	if response.Scenes == nil {
+		return nil, fmt.Errorf("scenes must be present")
+	}
+	if len(response.Scenes) == 0 {
+		return nil, fmt.Errorf("scenes must not be empty")
+	}
+
+	unitIndexes := make(map[string]int, len(doc.Units))
+	for i, unit := range doc.Units {
+		unitIndexes[unit.ID] = i
+	}
+
+	chunks := make([]contracts.SourceChunk, 0, len(response.Scenes))
+	previousEnd := -1
+	for i, scene := range response.Scenes {
+		normalized, err := normalizeScene(i, scene)
+		if err != nil {
+			return nil, err
+		}
+
+		startIndex, ok := unitIndexes[normalized.StartUnitID]
+		if !ok {
+			return nil, fmt.Errorf("scene[%d] start_unit_id %q was not found", i, normalized.StartUnitID)
+		}
+		endIndex, ok := unitIndexes[normalized.EndUnitID]
+		if !ok {
+			return nil, fmt.Errorf("scene[%d] end_unit_id %q was not found", i, normalized.EndUnitID)
+		}
+		if startIndex > endIndex {
+			return nil, fmt.Errorf("scene[%d] start_unit_id %q appears after end_unit_id %q", i, normalized.StartUnitID, normalized.EndUnitID)
+		}
+
+		if i == 0 && startIndex != 0 {
+			return nil, fmt.Errorf("first scene must start at first source unit %q", doc.Units[0].ID)
+		}
+		if i > 0 {
+			if startIndex <= previousEnd {
+				return nil, fmt.Errorf("scene[%d] overlaps previous scene", i)
+			}
+			if startIndex > previousEnd+1 {
+				return nil, fmt.Errorf("scene[%d] leaves a gap after previous scene", i)
+			}
+		}
+		previousEnd = endIndex
+
+		units := cloneUnits(doc.Units[startIndex : endIndex+1])
+		chunks = append(chunks, contracts.SourceChunk{
+			ID:       fmt.Sprintf("scene-%06d", i+1),
+			SourceID: doc.ID,
+			Index:    i,
+			Units:    units,
+			Metadata: map[string]any{
+				"scene_title":         normalized.ShortTitle,
+				"primary_mode":        normalized.PrimaryMode,
+				"main_participants":   append([]string(nil), normalized.MainParticipants...),
+				"summary":             normalized.Summary,
+				"boundary_note":       normalized.BoundaryNote,
+				"boundary_confidence": normalized.BoundaryConfidence,
+				"start_unit_id":       normalized.StartUnitID,
+				"end_unit_id":         normalized.EndUnitID,
+				"unit_count":          len(units),
+			},
+		})
+	}
+
+	if previousEnd != len(doc.Units)-1 {
+		return nil, fmt.Errorf("final scene must end at final source unit %q", doc.Units[len(doc.Units)-1].ID)
+	}
+	return chunks, nil
+}
+
+func normalizeScene(index int, scene sceneResponse) (sceneResponse, error) {
+	out := sceneResponse{
+		StartUnitID:        strings.TrimSpace(scene.StartUnitID),
+		EndUnitID:          strings.TrimSpace(scene.EndUnitID),
+		ShortTitle:         strings.TrimSpace(scene.ShortTitle),
+		PrimaryMode:        strings.TrimSpace(scene.PrimaryMode),
+		Summary:            strings.TrimSpace(scene.Summary),
+		BoundaryNote:       strings.TrimSpace(scene.BoundaryNote),
+		BoundaryConfidence: strings.TrimSpace(scene.BoundaryConfidence),
+	}
+
+	required := map[string]string{
+		"start_unit_id":       out.StartUnitID,
+		"end_unit_id":         out.EndUnitID,
+		"short_title":         out.ShortTitle,
+		"primary_mode":        out.PrimaryMode,
+		"summary":             out.Summary,
+		"boundary_note":       out.BoundaryNote,
+		"boundary_confidence": out.BoundaryConfidence,
+	}
+	for field, value := range required {
+		if value == "" {
+			return sceneResponse{}, fmt.Errorf("scene[%d] %s must not be empty", index, field)
+		}
+	}
+	if !validPrimaryMode(out.PrimaryMode) {
+		return sceneResponse{}, fmt.Errorf("scene[%d] primary_mode %q is not supported", index, out.PrimaryMode)
+	}
+	if !validBoundaryConfidence(out.BoundaryConfidence) {
+		return sceneResponse{}, fmt.Errorf("scene[%d] boundary_confidence %q is not supported", index, out.BoundaryConfidence)
+	}
+	if len(scene.MainParticipants) == 0 {
+		return sceneResponse{}, fmt.Errorf("scene[%d] main_participants must not be empty", index)
+	}
+	out.MainParticipants = make([]string, 0, len(scene.MainParticipants))
+	for participantIndex, participant := range scene.MainParticipants {
+		trimmed := strings.TrimSpace(participant)
+		if trimmed == "" {
+			return sceneResponse{}, fmt.Errorf("scene[%d] main_participants[%d] must not be empty", index, participantIndex)
+		}
+		out.MainParticipants = append(out.MainParticipants, trimmed)
+	}
+	return out, nil
+}
+
+func validPrimaryMode(value string) bool {
+	switch value {
+	case "Recap", "Discussion", "Combat", "Narrative":
+		return true
+	default:
+		return false
+	}
+}
+
+func validBoundaryConfidence(value string) bool {
+	switch value {
+	case "High", "Medium", "Low":
+		return true
+	default:
+		return false
+	}
+}
+
+func warningsFromCaveats(caveats []string) ([]contracts.Warning, error) {
+	if len(caveats) == 0 {
+		return nil, nil
+	}
+	warnings := make([]contracts.Warning, 0, len(caveats))
+	for i, caveat := range caveats {
+		trimmed := strings.TrimSpace(caveat)
+		if trimmed == "" {
+			return nil, fmt.Errorf("boundary_caveats[%d] must not be empty after trimming", i)
+		}
+		warnings = append(warnings, contracts.Warning{
+			Scope:      Key,
+			ReasonCode: "scene_boundary_caveat",
+			Message:    trimmed,
+		})
+	}
+	return warnings, nil
+}
+
+func cloneUnits(units []source.SourceUnit) []source.SourceUnit {
+	out := make([]source.SourceUnit, 0, len(units))
+	for _, unit := range units {
+		out = append(out, source.SourceUnit{
+			ID:       unit.ID,
+			Kind:     unit.Kind,
+			Text:     unit.Text,
+			Metadata: cloneMetadata(unit.Metadata),
+		})
+	}
+	return out
+}
+
+func cloneMetadata(metadata map[string]any) map[string]any {
+	if len(metadata) == 0 {
+		return nil
+	}
+	out := make(map[string]any, len(metadata))
+	for key, value := range metadata {
+		out[key] = value
+	}
+	return out
+}
+
+func chunkerErrorf(format string, args ...any) error {
+	return fmt.Errorf("dnd scenes chunker: "+format, args...)
+}

internal/modules/chunk/dnd/scenes/chunker_test.go

@@ -0,0 +1,484 @@
+package scenes
+
+import (
+	"bytes"
+	"context"
+	"encoding/json"
+	"errors"
+	"reflect"
+	"strings"
+	"testing"
+
+	"gitea.maximumdirect.net/eric/notarius/internal/core/source"
+	"gitea.maximumdirect.net/eric/notarius/internal/framework/contracts"
+	"gitea.maximumdirect.net/eric/notarius/internal/framework/pipeline"
+)
+
+func TestNewModuleSpecAndRegister(t *testing.T) {
+	chunker := New()
+	if chunker == nil {
+		t.Fatal("New() = nil, want chunker")
+	}
+	if chunker.Key() != Key {
+		t.Fatalf("Key() = %q, want %q", chunker.Key(), Key)
+	}
+
+	want := pipeline.ModuleSpec{
+		Key:      Key,
+		Stage:    pipeline.StageChunk,
+		Requires: []string{"source.transcript"},
+		Provides: []string{"chunks", "chunks.scenes"},
+	}
+	if got := ModuleSpec(); !reflect.DeepEqual(got, want) {
+		t.Fatalf("ModuleSpec() = %#v, want %#v", got, want)
+	}
+	got := ModuleSpec()
+	got.Requires[0] = "changed"
+	got.Provides[0] = "changed"
+	if again := ModuleSpec(); !reflect.DeepEqual(again, want) {
+		t.Fatalf("ModuleSpec() after caller mutation = %#v, want %#v", again, want)
+	}
+
+	registry := pipeline.NewChunkerRegistry()
+	if err := Register(registry); err != nil {
+		t.Fatalf("Register() error = %v, want nil", err)
+	}
+	registered, ok := registry.Spec(Key)
+	if !ok {
+		t.Fatalf("Spec(%q) ok = false, want true", Key)
+	}
+	if !reflect.DeepEqual(registered, want) {
+		t.Fatalf("registered spec = %#v, want %#v", registered, want)
+	}
+	built, err := registry.Build(Key)
+	if err != nil {
+		t.Fatalf("Build(%q) error = %v, want nil", Key, err)
+	}
+	if built.Key() != Key {
+		t.Fatalf("built Key() = %q, want %q", built.Key(), Key)
+	}
+}
+
+func TestRegisterNilRegistryReturnsError(t *testing.T) {
+	err := Register(nil)
+	if err == nil {
+		t.Fatal("Register(nil) error = nil, want error")
+	}
+	if !strings.Contains(err.Error(), "chunker registry") {
+		t.Fatalf("Register(nil) error = %q, want registry context", err.Error())
+	}
+}
+
+func TestChunkReturnsSceneChunksFromStructuredOutput(t *testing.T) {
+	client := &fakeScenesLLMClient{
+		response: chunkResponse{
+			Scenes: []sceneResponse{
+				{
+					StartUnitID:        "seg-001",
+					EndUnitID:          "seg-002",
+					ShortTitle:         " Goblin parley ",
+					PrimaryMode:        "Discussion",
+					MainParticipants:   []string{" Aria ", "Goblin scout"},
+					Summary:            " The party negotiates with a scout. ",
+					BoundaryNote:       " The scene covers the discussion before fighting starts. ",
+					BoundaryConfidence: "High",
+				},
+				{
+					StartUnitID:        "seg-003",
+					EndUnitID:          "seg-004",
+					ShortTitle:         "Ambush at the gate",
+					PrimaryMode:        "Combat",
+					MainParticipants:   []string{"Aria", "Goblin ambushers"},
+					Summary:            "The goblins attack at the gate.",
+					BoundaryNote:       "Combat begins and resolves the immediate threat.",
+					BoundaryConfidence: "Medium",
+				},
+			},
+			BoundaryCaveats: []string{" The transition into combat is gradual. "},
+		},
+	}
+
+	result, err := New().Chunk(context.Background(), chunkRequestWithClient(client))
+	if err != nil {
+		t.Fatalf("Chunk() error = %v, want nil", err)
+	}
+
+	if len(client.requests) != 1 {
+		t.Fatalf("LLM calls = %d, want 1", len(client.requests))
+	}
+	req := client.requests[0]
+	if req.StageName != Key {
+		t.Fatalf("StageName = %q, want %q", req.StageName, Key)
+	}
+	schema, err := loadResponseSchema()
+	if err != nil {
+		t.Fatalf("loadResponseSchema() error = %v, want nil", err)
+	}
+	if req.ResponseSchemaName != schema.Name {
+		t.Fatalf("ResponseSchemaName = %q, want %q", req.ResponseSchemaName, schema.Name)
+	}
+	if !bytes.Equal(req.ResponseSchema, schema.JSONSchema) {
+		t.Fatal("ResponseSchema does not match D&D scenes schema")
+	}
+	if len(req.Messages) != 2 || req.Messages[0].Role != "system" || req.Messages[1].Role != "user" {
+		t.Fatalf("Messages = %#v, want system then user", req.Messages)
+	}
+	for _, want := range []string{"session-alpha", "seg-001", "seg-004", "start_unit_id", "boundary_confidence"} {
+		if !strings.Contains(req.Messages[1].Content, want) {
+			t.Fatalf("user message = %q, want substring %q", req.Messages[1].Content, want)
+		}
+	}
+
+	if got := chunkIDs(result.Chunks); !reflect.DeepEqual(got, []string{"scene-000001", "scene-000002"}) {
+		t.Fatalf("chunk IDs = %#v, want deterministic scene IDs", got)
+	}
+	gotUnits := [][]string{unitIDs(result.Chunks[0].Units), unitIDs(result.Chunks[1].Units)}
+	wantUnits := [][]string{{"seg-001", "seg-002"}, {"seg-003", "seg-004"}}
+	if !reflect.DeepEqual(gotUnits, wantUnits) {
+		t.Fatalf("chunk units = %#v, want %#v", gotUnits, wantUnits)
+	}
+	first := result.Chunks[0]
+	if first.SourceID != "session-alpha" || first.Index != 0 {
+		t.Fatalf("first chunk = %#v, want source and index fields", first)
+	}
+	if first.Metadata["scene_title"] != "Goblin parley" ||
+		first.Metadata["primary_mode"] != "Discussion" ||
+		first.Metadata["summary"] != "The party negotiates with a scout." ||
+		first.Metadata["boundary_note"] != "The scene covers the discussion before fighting starts." ||
+		first.Metadata["boundary_confidence"] != "High" ||
+		first.Metadata["start_unit_id"] != "seg-001" ||
+		first.Metadata["end_unit_id"] != "seg-002" ||
+		first.Metadata["unit_count"] != 2 {
+		t.Fatalf("first metadata = %#v, want scene metadata", first.Metadata)
+	}
+	if got, ok := first.Metadata["main_participants"].([]string); !ok || !reflect.DeepEqual(got, []string{"Aria", "Goblin scout"}) {
+		t.Fatalf("main_participants = %#v, want trimmed participant slice", first.Metadata["main_participants"])
+	}
+	if got := result.Warnings; len(got) != 1 ||
+		got[0].Scope != Key ||
+		got[0].ReasonCode != "scene_boundary_caveat" ||
+		got[0].Message != "The transition into combat is gradual." {
+		t.Fatalf("Warnings = %#v, want boundary caveat warning", got)
+	}
+}
+
+func TestChunkRejectsWhitespaceOnlyBoundaryCaveats(t *testing.T) {
+	client := &fakeScenesLLMClient{
+		response: chunkResponse{
+			Scenes: validSceneResponse().Scenes,
+			BoundaryCaveats: []string{
+				"   ",
+			},
+		},
+	}
+
+	_, err := New().Chunk(context.Background(), chunkRequestWithClient(client))
+	if err == nil {
+		t.Fatal("Chunk() error = nil, want malformed structured output error")
+	}
+	if !strings.Contains(err.Error(), "dnd scenes chunker") || !strings.Contains(err.Error(), "malformed structured output") || !strings.Contains(err.Error(), "boundary_caveats[0]") {
+		t.Fatalf("Chunk() error = %q, want malformed boundary caveat context", err.Error())
+	}
+}
+
+func TestChunkDefensivelyCopiesSourceUnitsAndMetadata(t *testing.T) {
+	doc := sceneSourceDocument()
+	client := &fakeScenesLLMClient{response: validSceneResponse()}
+
+	result, err := New().Chunk(context.Background(), contracts.ChunkRequest{
+		Source:    doc,
+		LLMClient: client,
+	})
+	if err != nil {
+		t.Fatalf("Chunk() error = %v, want nil", err)
+	}
+
+	doc.Units[0].ID = "mutated"
+	doc.Units[0].Metadata["speaker"] = "mutated"
+	client.response.Scenes[0].MainParticipants[0] = "mutated"
+
+	if result.Chunks[0].Units[0].ID != "seg-001" {
+		t.Fatalf("chunk unit ID changed after source mutation: %#v", result.Chunks[0].Units[0])
+	}
+	if result.Chunks[0].Units[0].Metadata["speaker"] != "Alice" {
+		t.Fatalf("chunk unit metadata changed after source mutation: %#v", result.Chunks[0].Units[0].Metadata)
+	}
+	participants, ok := result.Chunks[0].Metadata["main_participants"].([]string)
+	if !ok || participants[0] != "Aria" {
+		t.Fatalf("participants = %#v, want defensive copy", result.Chunks[0].Metadata["main_participants"])
+	}
+}
+
+func TestChunkerManifestMetadataIncludesPromptAndSchemaProvenance(t *testing.T) {
+	metadata := New().ManifestMetadata()
+
+	tests := map[string]string{
+		"prompt_id":               PromptID,
+		"prompt_version":          ResponseSchemaVersion,
+		"response_schema_key":     string(ResponseSchemaKey),
+		"response_schema_id":      ResponseSchemaID,
+		"response_schema_name":    ResponseSchemaName,
+		"response_schema_version": ResponseSchemaVersion,
+	}
+	for key, want := range tests {
+		if metadata[key] != want {
+			t.Fatalf("metadata[%q] = %#v, want %q", key, metadata[key], want)
+		}
+	}
+	for _, key := range []string{"prompt_sha256", "response_schema_sha256"} {
+		value, ok := metadata[key].(string)
+		if !ok || !strings.HasPrefix(value, "sha256:") {
+			t.Fatalf("metadata[%q] = %#v, want sha256 value", key, metadata[key])
+		}
+	}
+	for _, forbidden := range []string{"prompt", "schema", "source", "text"} {
+		if _, ok := metadata[forbidden]; ok {
+			t.Fatalf("metadata includes raw %q field: %#v", forbidden, metadata)
+		}
+	}
+}
+
+func TestChunkRejectsInvalidRequests(t *testing.T) {
+	validClient := &fakeScenesLLMClient{response: validSceneResponse()}
+	validReq := chunkRequestWithClient(validClient)
+	canceledCtx, cancel := context.WithCancel(context.Background())
+	cancel()
+	invalidDoc := sceneSourceDocument()
+	invalidDoc.Units[0].ID = ""
+	emptyDoc := sceneSourceDocument()
+	emptyDoc.Units = nil
+
+	tests := []struct {
+		name    string
+		chunker *Chunker
+		ctx     context.Context
+		req     contracts.ChunkRequest
+		want    string
+	}{
+		{name: "nil chunker", chunker: nil, ctx: context.Background(), req: validReq, want: "chunker"},
+		{name: "nil context", chunker: New(), ctx: nil, req: validReq, want: "context"},
+		{name: "canceled context", chunker: New(), ctx: canceledCtx, req: validReq, want: "context"},
+		{name: "nil source", chunker: New(), ctx: context.Background(), req: contracts.ChunkRequest{LLMClient: validClient}, want: "source"},
+		{name: "empty source units", chunker: New(), ctx: context.Background(), req: contracts.ChunkRequest{Source: emptyDoc, LLMClient: validClient}, want: "units"},
+		{name: "invalid source", chunker: New(), ctx: context.Background(), req: contracts.ChunkRequest{Source: invalidDoc, LLMClient: validClient}, want: "validate source document"},
+		{name: "nil LLM client", chunker: New(), ctx: context.Background(), req: contracts.ChunkRequest{Source: sceneSourceDocument()}, want: "LLM client"},
+		{name: "unsupported options", chunker: New(), ctx: context.Background(), req: requestWithOptions(validReq), want: "options"},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			_, err := tt.chunker.Chunk(tt.ctx, tt.req)
+			if err == nil {
+				t.Fatal("Chunk() error = nil, want error")
+			}
+			if !strings.Contains(err.Error(), "dnd scenes") || !strings.Contains(err.Error(), tt.want) {
+				t.Fatalf("Chunk() error = %q, want module context and %q", err.Error(), tt.want)
+			}
+		})
+	}
+}
+
+func TestChunkRejectsMalformedStructuredOutput(t *testing.T) {
+	tests := []struct {
+		name     string
+		response chunkResponse
+		want     string
+	}{
+		{name: "missing scenes", response: chunkResponse{}, want: "scenes"},
+		{name: "empty scenes", response: chunkResponse{Scenes: []sceneResponse{}}, want: "scenes"},
+		{
+			name: "unknown boundary id",
+			response: replaceScenes(validSceneResponse(), []sceneResponse{
+				scene("seg-001", "seg-999"),
+			}),
+			want: "was not found",
+		},
+		{
+			name: "out of order boundaries",
+			response: replaceScenes(validSceneResponse(), []sceneResponse{
+				scene("seg-003", "seg-002"),
+			}),
+			want: "appears after",
+		},
+		{
+			name: "gap",
+			response: replaceScenes(validSceneResponse(), []sceneResponse{
+				scene("seg-001", "seg-001"),
+				scene("seg-003", "seg-004"),
+			}),
+			want: "gap",
+		},
+		{
+			name: "overlap",
+			response: replaceScenes(validSceneResponse(), []sceneResponse{
+				scene("seg-001", "seg-002"),
+				scene("seg-002", "seg-004"),
+			}),
+			want: "overlap",
+		},
+		{
+			name: "incomplete coverage",
+			response: replaceScenes(validSceneResponse(), []sceneResponse{
+				scene("seg-001", "seg-003"),
+			}),
+			want: "final scene",
+		},
+		{
+			name: "empty metadata field",
+			response: replaceScenes(validSceneResponse(), []sceneResponse{
+				{
+					StartUnitID:        "seg-001",
+					EndUnitID:          "seg-004",
+					ShortTitle:         " ",
+					PrimaryMode:        "Narrative",
+					MainParticipants:   []string{"Aria"},
+					Summary:            "Summary.",
+					BoundaryNote:       "Note.",
+					BoundaryConfidence: "High",
+				},
+			}),
+			want: "short_title",
+		},
+		{
+			name: "empty participant",
+			response: replaceScenes(validSceneResponse(), []sceneResponse{
+				{
+					StartUnitID:        "seg-001",
+					EndUnitID:          "seg-004",
+					ShortTitle:         "Title",
+					PrimaryMode:        "Narrative",
+					MainParticipants:   []string{"Aria", " "},
+					Summary:            "Summary.",
+					BoundaryNote:       "Note.",
+					BoundaryConfidence: "High",
+				},
+			}),
+			want: "main_participants",
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			client := &fakeScenesLLMClient{response: tt.response}
+			_, err := New().Chunk(context.Background(), chunkRequestWithClient(client))
+			if err == nil {
+				t.Fatal("Chunk() error = nil, want error")
+			}
+			if !strings.Contains(err.Error(), "dnd scenes") || !strings.Contains(err.Error(), tt.want) {
+				t.Fatalf("Chunk() error = %q, want module context and %q", err.Error(), tt.want)
+			}
+		})
+	}
+}
+
+func TestChunkWrapsLLMClientError(t *testing.T) {
+	client := &fakeScenesLLMClient{err: errors.New("provider unavailable")}
+
+	_, err := New().Chunk(context.Background(), chunkRequestWithClient(client))
+	if err == nil {
+		t.Fatal("Chunk() error = nil, want LLM error")
+	}
+	if !strings.Contains(err.Error(), "dnd scenes") || !strings.Contains(err.Error(), "provider unavailable") {
+		t.Fatalf("Chunk() error = %q, want wrapped LLM context", err.Error())
+	}
+}
+
+func chunkRequestWithClient(client contracts.StructuredLLMClient) contracts.ChunkRequest {
+	return contracts.ChunkRequest{
+		Source:    sceneSourceDocument(),
+		LLMClient: client,
+	}
+}
+
+func requestWithOptions(req contracts.ChunkRequest) contracts.ChunkRequest {
+	req.Options = map[string]any{"max_units": 2}
+	return req
+}
+
+func sceneSourceDocument() *source.SourceDocument {
+	return &source.SourceDocument{
+		ID:     "session-alpha",
+		Kind:   "transcript",
+		Format: "application/vnd.seriatim.minimal+json",
+		Digest: "sha256:source",
+		Units: []source.SourceUnit{
+			{ID: "seg-001", Kind: "transcript_segment", Text: "Aria asks whether the goblin will parley.", Metadata: map[string]any{"speaker": "Alice"}},
+			{ID: "seg-002", Kind: "transcript_segment", Text: "The goblin scout describes the gate guards."},
+			{ID: "seg-003", Kind: "transcript_segment", Text: "The guards rush out with blades drawn."},
+			{ID: "seg-004", Kind: "transcript_segment", Text: "The party defeats the ambushers."},
+		},
+	}
+}
+
+func validSceneResponse() chunkResponse {
+	return chunkResponse{
+		Scenes: []sceneResponse{
+			scene("seg-001", "seg-004"),
+		},
+		BoundaryCaveats: []string{},
+	}
+}
+
+func replaceScenes(response chunkResponse, scenes []sceneResponse) chunkResponse {
+	response.Scenes = scenes
+	return response
+}
+
+func scene(startUnitID string, endUnitID string) sceneResponse {
+	return sceneResponse{
+		StartUnitID:        startUnitID,
+		EndUnitID:          endUnitID,
+		ShortTitle:         "Scene title",
+		PrimaryMode:        "Narrative",
+		MainParticipants:   []string{"Aria"},
+		Summary:            "A compact summary.",
+		BoundaryNote:       "The source units form one coherent scene.",
+		BoundaryConfidence: "High",
+	}
+}
+
+func chunkIDs(chunks []contracts.SourceChunk) []string {
+	ids := make([]string, 0, len(chunks))
+	for _, chunk := range chunks {
+		ids = append(ids, chunk.ID)
+	}
+	return ids
+}
+
+func unitIDs(units []source.SourceUnit) []string {
+	ids := make([]string, 0, len(units))
+	for _, unit := range units {
+		ids = append(ids, unit.ID)
+	}
+	return ids
+}
+
+type fakeScenesLLMClient struct {
+	response chunkResponse
+	err      error
+	requests []contracts.StructuredCompletionRequest
+}
+
+func (client *fakeScenesLLMClient) CompleteStructured(ctx context.Context, req contracts.StructuredCompletionRequest, out any) (contracts.StructuredCompletionResponse, error) {
+	client.requests = append(client.requests, contracts.StructuredCompletionRequest{
+		StageName:          req.StageName,
+		Messages:           append([]contracts.LLMMessage(nil), req.Messages...),
+		Model:              req.Model,
+		ResponseSchemaName: req.ResponseSchemaName,
+		ResponseSchema:     append(json.RawMessage(nil), req.ResponseSchema...),
+	})
+	if client.err != nil {
+		return contracts.StructuredCompletionResponse{}, client.err
+	}
+
+	target, ok := out.(*chunkResponse)
+	if !ok {
+		return contracts.StructuredCompletionResponse{}, errors.New("unexpected output target")
+	}
+	*target = client.response
+	content, err := json.Marshal(client.response)
+	if err != nil {
+		return contracts.StructuredCompletionResponse{}, err
+	}
+	return contracts.StructuredCompletionResponse{Content: content}, nil
+}

internal/modules/chunk/dnd/scenes/model.go

@@ -0,0 +1,17 @@
+package scenes
+
+type chunkResponse struct {
+	Scenes          []sceneResponse `json:"scenes"`
+	BoundaryCaveats []string        `json:"boundary_caveats"`
+}
+
+type sceneResponse struct {
+	StartUnitID        string   `json:"start_unit_id"`
+	EndUnitID          string   `json:"end_unit_id"`
+	ShortTitle         string   `json:"short_title"`
+	PrimaryMode        string   `json:"primary_mode"`
+	MainParticipants   []string `json:"main_participants"`
+	Summary            string   `json:"summary"`
+	BoundaryNote       string   `json:"boundary_note"`
+	BoundaryConfidence string   `json:"boundary_confidence"`
+}

internal/modules/chunk/dnd/scenes/prompt.go

@@ -0,0 +1,97 @@
+package scenes
+
+import (
+	"fmt"
+	"strings"
+
+	"gitea.maximumdirect.net/eric/notarius/internal/core/source"
+	"gitea.maximumdirect.net/eric/notarius/internal/framework/contracts"
+	"gitea.maximumdirect.net/eric/notarius/internal/framework/prompt"
+)
+
+type promptData struct {
+	SourceID string
+	Units    []promptUnit
+}
+
+type promptUnit struct {
+	ID       string
+	Text     string
+	Metadata []promptMetadata
+}
+
+type promptMetadata struct {
+	Key   string
+	Value string
+}
+
+var scenesPromptBundle = mustLoadPromptBundle()
+
+func mustLoadPromptBundle() *prompt.Bundle {
+	bundle, err := prompt.LoadBundle(embeddedAssets, prompt.Definition{
+		PromptID:     PromptID,
+		Version:      ResponseSchemaVersion,
+		EmbeddedPath: "assets/prompts",
+		SystemPath:   "assets/prompts/system.md",
+		UserPath:     "assets/prompts/user.md",
+	})
+	if err != nil {
+		panic(err)
+	}
+	return bundle
+}
+
+func buildPromptData(req contracts.ChunkRequest) (promptData, error) {
+	if req.Source == nil {
+		return promptData{}, fmt.Errorf("dnd scenes prompt: source must not be nil")
+	}
+
+	data := promptData{
+		SourceID: req.Source.ID,
+		Units:    make([]promptUnit, 0, len(req.Source.Units)),
+	}
+	for _, unit := range req.Source.Units {
+		data.Units = append(data.Units, promptUnit{
+			ID:       unit.ID,
+			Text:     unit.Text,
+			Metadata: selectedMetadata(unit),
+		})
+	}
+	return data, nil
+}
+
+func renderPrompt(req contracts.ChunkRequest) (system string, user string, metadata prompt.Metadata, err error) {
+	data, err := buildPromptData(req)
+	if err != nil {
+		return "", "", prompt.Metadata{}, err
+	}
+	system, user, metadata, err = scenesPromptBundle.RenderUserSystem(data)
+	if err != nil {
+		return "", "", prompt.Metadata{}, fmt.Errorf("dnd scenes prompt: %w", err)
+	}
+	return system, user, metadata, nil
+}
+
+func selectedMetadata(unit source.SourceUnit) []promptMetadata {
+	if len(unit.Metadata) == 0 {
+		return nil
+	}
+
+	keys := []string{"speaker", "start", "end"}
+	metadata := make([]promptMetadata, 0, len(keys))
+	for _, key := range keys {
+		value, ok := unit.Metadata[key]
+		if !ok {
+			continue
+		}
+		rendered := strings.TrimSpace(fmt.Sprint(value))
+		if rendered == "" {
+			continue
+		}
+		metadata = append(metadata, promptMetadata{
+			Key:   key,
+			Value: rendered,
+		})
+	}
+	return metadata
+}

internal/modules/chunk/dnd/scenes/prompt_test.go

@@ -0,0 +1,155 @@
+package scenes
+
+import (
+	"encoding/json"
+	"reflect"
+	"strings"
+	"testing"
+
+	"gitea.maximumdirect.net/eric/notarius/internal/core/source"
+	"gitea.maximumdirect.net/eric/notarius/internal/framework/contracts"
+	"gitea.maximumdirect.net/eric/notarius/internal/framework/prompt"
+)
+
+func TestBuildPromptDataFromSourceDocument(t *testing.T) {
+	req := promptChunkRequest()
+
+	data, err := buildPromptData(req)
+	if err != nil {
+		t.Fatalf("buildPromptData() error = %v, want nil", err)
+	}
+
+	if data.SourceID != "session-alpha" {
+		t.Fatalf("SourceID = %q, want session-alpha", data.SourceID)
+	}
+	if len(data.Units) != 2 {
+		t.Fatalf("len(Units) = %d, want 2", len(data.Units))
+	}
+	first := data.Units[0]
+	if first.ID != "seg-001" || first.Text != "Aria and Bram discuss whether to enter the ruins." {
+		t.Fatalf("first unit = %#v, want source unit data", first)
+	}
+	wantMetadata := []promptMetadata{
+		{Key: "speaker", Value: "Alice"},
+		{Key: "start", Value: "1.25"},
+		{Key: "end", Value: "3.5"},
+	}
+	if !reflect.DeepEqual(first.Metadata, wantMetadata) {
+		t.Fatalf("first.Metadata = %#v, want %#v", first.Metadata, wantMetadata)
+	}
+	if len(data.Units[1].Metadata) != 0 {
+		t.Fatalf("second.Metadata = %#v, want no selected metadata", data.Units[1].Metadata)
+	}
+}
+
+func TestBuildPromptDataDoesNotMutateRequest(t *testing.T) {
+	req := promptChunkRequest()
+	beforeSource := mustJSON(t, req.Source)
+	beforeRequest := mustJSON(t, req)
+
+	if _, err := buildPromptData(req); err != nil {
+		t.Fatalf("buildPromptData() error = %v, want nil", err)
+	}
+	afterSource := mustJSON(t, req.Source)
+	afterRequest := mustJSON(t, req)
+	if beforeSource != afterSource || beforeRequest != afterRequest {
+		t.Fatalf(
+			"request mutated:\nsource before: %s\nsource after:  %s\nrequest before: %s\nrequest after:  %s",
+			beforeSource,
+			afterSource,
+			beforeRequest,
+			afterRequest,
+		)
+	}
+}
+
+func TestRenderPromptIncludesSourceUnitsAndMetadata(t *testing.T) {
+	system, user, metadata, err := renderPrompt(promptChunkRequest())
+	if err != nil {
+		t.Fatalf("renderPrompt() error = %v, want nil", err)
+	}
+
+	if !strings.Contains(system, prompt.HardeningText()) {
+		t.Fatalf("system prompt = %q, want hardening text", system)
+	}
+	for _, want := range []string{
+		"session-alpha",
+		"seg-001",
+		"seg-002",
+		"Aria and Bram discuss whether to enter the ruins.",
+		"The goblins rush out and initiative begins.",
+		"speaker: Alice",
+		"start: 1.25",
+		"end: 3.5",
+		"start_unit_id",
+		"end_unit_id",
+		"primary_mode",
+		"boundary_confidence",
+		"Recap, Discussion, Combat, or Narrative",
+		"High, Medium, or Low",
+		"no gaps",
+		"do not overlap",
+	} {
+		if !strings.Contains(user, want) {
+			t.Fatalf("user prompt = %q, want substring %q", user, want)
+		}
+	}
+	if metadata.PromptID != PromptID {
+		t.Fatalf("metadata.PromptID = %q, want %q", metadata.PromptID, PromptID)
+	}
+	if metadata.PromptVersion != ResponseSchemaVersion {
+		t.Fatalf("metadata.PromptVersion = %q, want %q", metadata.PromptVersion, ResponseSchemaVersion)
+	}
+	if metadata.EmbeddedPath != "assets/prompts" {
+		t.Fatalf("metadata.EmbeddedPath = %q, want assets/prompts", metadata.EmbeddedPath)
+	}
+}
+
+func TestBuildPromptDataRejectsMissingSourceContext(t *testing.T) {
+	if _, err := buildPromptData(contracts.ChunkRequest{}); err == nil || !strings.Contains(err.Error(), "source") {
+		t.Fatalf("buildPromptData() error = %v, want source error", err)
+	}
+}
+
+func promptChunkRequest() contracts.ChunkRequest {
+	return contracts.ChunkRequest{
+		Source: promptSourceDocument(),
+	}
+}
+
+func promptSourceDocument() *source.SourceDocument {
+	return &source.SourceDocument{
+		ID:     "session-alpha",
+		Kind:   "transcript",
+		Format: "application/vnd.seriatim.minimal+json",
+		Digest: "sha256:test",
+		Units: []source.SourceUnit{
+			{
+				ID:   "seg-001",
+				Kind: "transcript_segment",
+				Text: "Aria and Bram discuss whether to enter the ruins.",
+				Metadata: map[string]any{
+					"speaker": "Alice",
+					"start":   json.Number("1.25"),
+					"end":     json.Number("3.5"),
+					"ignored": "not rendered",
+				},
+			},
+			{
+				ID:       "seg-002",
+				Kind:     "transcript_segment",
+				Text:     "The goblins rush out and initiative begins.",
+				Metadata: map[string]any{"ignored": "not rendered"},
+			},
+		},
+	}
+}
+
+func mustJSON(t *testing.T, value any) string {
+	t.Helper()
+	encoded, err := json.Marshal(value)
+	if err != nil {
+		t.Fatalf("Marshal() error = %v, want nil", err)
+	}
+	return string(encoded)
+}

internal/modules/chunk/dnd/scenes/schema.go

@@ -0,0 +1,21 @@
+package scenes
+
+import "gitea.maximumdirect.net/eric/notarius/internal/framework/llm"
+
+const (
+	PromptID              = "dnd.scenes"
+	ResponseSchemaKey     = llm.ResponseSchemaKey("dnd_scenes")
+	ResponseSchemaID      = "notarius.dnd.scenes"
+	ResponseSchemaVersion = "v1"
+	ResponseSchemaName    = "notarius_dnd_scenes_v1"
+)
+
+func loadResponseSchema() (llm.ResponseSchema, error) {
+	return llm.LoadResponseSchema(embeddedAssets, llm.ResponseSchemaDefinition{
+		Key:       ResponseSchemaKey,
+		ID:        ResponseSchemaID,
+		Version:   ResponseSchemaVersion,
+		Name:      ResponseSchemaName,
+		AssetPath: "assets/schemas/dnd_scenes.v1.json",
+	})
+}

internal/modules/chunk/dnd/scenes/schema_test.go

@@ -0,0 +1,146 @@
+package scenes
+
+import (
+	"encoding/json"
+	"strings"
+	"testing"
+)
+
+func TestLoadResponseSchemaForScenes(t *testing.T) {
+	schema, err := loadResponseSchema()
+	if err != nil {
+		t.Fatalf("loadResponseSchema() error = %v, want nil", err)
+	}
+	if schema.Key != ResponseSchemaKey {
+		t.Fatalf("schema.Key = %q, want %q", schema.Key, ResponseSchemaKey)
+	}
+	if schema.ID != ResponseSchemaID {
+		t.Fatalf("schema.ID = %q, want %q", schema.ID, ResponseSchemaID)
+	}
+	if schema.Version != ResponseSchemaVersion {
+		t.Fatalf("schema.Version = %q, want %q", schema.Version, ResponseSchemaVersion)
+	}
+	if schema.Name != ResponseSchemaName {
+		t.Fatalf("schema.Name = %q, want %q", schema.Name, ResponseSchemaName)
+	}
+	if !strings.HasPrefix(schema.SHA256, "sha256:") {
+		t.Fatalf("schema.SHA256 = %q, want sha256 prefix", schema.SHA256)
+	}
+	if !json.Valid(schema.JSONSchema) {
+		t.Fatalf("schema.JSONSchema is invalid JSON: %s", schema.JSONSchema)
+	}
+}
+
+func TestResponseSchemaShapeUsesSourceUnitBoundaries(t *testing.T) {
+	schema, err := loadResponseSchema()
+	if err != nil {
+		t.Fatalf("loadResponseSchema() error = %v, want nil", err)
+	}
+
+	var decoded map[string]any
+	if err := json.Unmarshal(schema.JSONSchema, &decoded); err != nil {
+		t.Fatalf("Unmarshal() error = %v, want nil", err)
+	}
+	if decoded["$id"] != ResponseSchemaID {
+		t.Fatalf("$id = %#v, want %q", decoded["$id"], ResponseSchemaID)
+	}
+	if decoded["additionalProperties"] != false {
+		t.Fatalf("additionalProperties = %#v, want false", decoded["additionalProperties"])
+	}
+
+	properties := decoded["properties"].(map[string]any)
+	if _, ok := properties["artifact_type"]; ok {
+		t.Fatal("schema includes artifact_type, want only scene response fields")
+	}
+	if _, ok := properties["session_scope"]; ok {
+		t.Fatal("schema includes session_scope, want no session wrapper")
+	}
+
+	sceneProperties := properties["scenes"].(map[string]any)["items"].(map[string]any)["properties"].(map[string]any)
+	for _, field := range []string{"scene_id", "start_segment_id", "end_segment_id"} {
+		if _, ok := sceneProperties[field]; ok {
+			t.Fatalf("scene schema includes old field %q", field)
+		}
+	}
+	for _, field := range []string{"start_unit_id", "end_unit_id"} {
+		property := sceneProperties[field].(map[string]any)
+		if property["type"] != "string" {
+			t.Fatalf("%s type = %#v, want string", field, property["type"])
+		}
+	}
+
+	modeEnum := sceneProperties["primary_mode"].(map[string]any)["enum"].([]any)
+	if !sameStrings(modeEnum, []string{"Recap", "Discussion", "Combat", "Narrative"}) {
+		t.Fatalf("primary_mode enum = %#v, want Recap/Discussion/Combat/Narrative", modeEnum)
+	}
+	confidenceEnum := sceneProperties["boundary_confidence"].(map[string]any)["enum"].([]any)
+	if !sameStrings(confidenceEnum, []string{"High", "Medium", "Low"}) {
+		t.Fatalf("boundary_confidence enum = %#v, want High/Medium/Low", confidenceEnum)
+	}
+
+	boundaryCaveatItems := decoded["properties"].(map[string]any)["boundary_caveats"].(map[string]any)["items"].(map[string]any)
+	if boundaryCaveatItems["type"] != "string" {
+		t.Fatalf("boundary_caveats.items.type = %#v, want string", boundaryCaveatItems["type"])
+	}
+	if boundaryCaveatItems["minLength"] != float64(1) {
+		t.Fatalf("boundary_caveats.items.minLength = %#v, want 1", boundaryCaveatItems["minLength"])
+	}
+}
+
+func TestResponseStructRejectsIntegerBoundaries(t *testing.T) {
+	raw := []byte(`{
+		"scenes": [
+			{
+				"start_unit_id": 1,
+				"end_unit_id": 3,
+				"short_title": "Ambush",
+				"primary_mode": "Combat",
+				"main_participants": ["Aria"],
+				"summary": "The party fights.",
+				"boundary_note": "Combat starts and resolves.",
+				"boundary_confidence": "High"
+			}
+		],
+		"boundary_caveats": []
+	}`)
+
+	var response chunkResponse
+	err := json.Unmarshal(raw, &response)
+	if err == nil {
+		t.Fatalf("Unmarshal() error = nil, want integer boundary type error: %#v", response)
+	}
+	if !strings.Contains(err.Error(), "string") {
+		t.Fatalf("Unmarshal() error = %v, want string type error", err)
+	}
+}
+
+func TestResponseSchemaJSONIsMutationSafe(t *testing.T) {
+	first, err := loadResponseSchema()
+	if err != nil {
+		t.Fatalf("loadResponseSchema() error = %v, want nil", err)
+	}
+	first.JSONSchema[0] = '['
+
+	second, err := loadResponseSchema()
+	if err != nil {
+		t.Fatalf("loadResponseSchema() error = %v, want nil", err)
+	}
+	if !json.Valid(second.JSONSchema) {
+		t.Fatalf("schema JSON was mutated: %s", second.JSONSchema)
+	}
+	if len(second.JSONSchema) > 0 && second.JSONSchema[0] == '[' {
+		t.Fatalf("schema JSON did not use defensive copy")
+	}
+}
+
+func sameStrings(got []any, want []string) bool {
+	if len(got) != len(want) {
+		return false
+	}
+	for i := range want {
+		if got[i] != want[i] {
+			return false
+		}
+	}
+	return true
+}